I'm sure there's an obvious answer to this, but does anyone know of a website where one can make private, confidential bets and then be reminded to judge the outcome? And then over time a rough measure of your calibration would occur?
For context, I'm a doctor, and I'd like to improve my clinical reasoning by making private bets (e.g. diagnosis, prognosis, confidence) with myself and then resolving them later (e.g. by reviewing test results). Would be great if there was a system that automated this to some extent, while being appropriately secure and confidential.
E) Walk & Talk: We usually have an hour-long walk and talk after the meeting starts. Two mini-malls with hot takeout food are easily accessible nearby. Search for Gelson's or Pavilions in the zip code 92660.
F) Share a Surprise: Tell the group about something unexpected or that changed your perspective on the universe.
G) Future Direction Ideas: Contribute ideas for the group's future direction, including topics, meeting types, activities, etc.
I had also thought that cost per square foot was the better metric. Some quick Googling says that cost per square foot is about double or more in Japan, even city center to city center.
Similar Googling says that the average home size in Japan is about half the size of a home in the US. That should result in comparable prices at the macro level, though I would bet on significant differences in individual residences.
Any thoughts on Netflix’s “Take Care of Maya”? I saw the documentary and I am not sure what to think. On the one hand it seems terrible what happened to the family, but you have to wonder about the Ketamine treatment. Just curious what others think.
No opinion on the specific treatment, just a general opinion that if the official treatments do not work, people should be allowed to try unofficial ones.
I watched "Sharp Objects" and "Take Care of Maya" soon after each other, it is an interesting combination (trying to avoid spoilers).
Reason, a libertarian news organization, made a video reporting on Próspera, the ZEDE charter city Scott talked about a while ago: https://www.youtube.com/watch?v=TwiE1dxGYNY
Using surveys to investigate if kindness in general is going up or down is just as questionable as using surveys to investigate if moral more generally is going up or down. In both cases, survey methodology is riddled with two problems: the problem of non- attitudes (many people do not actually have opinions on such questions - they give off-the-cuff responses to be polite. Their responses are therefore low quality, and not stable if you ask them again even after a short time interval. This is the research tradition after Philip E Converse); and pluralistic ignorance (people take their cues from mass media when they answer such general questions, not from their own life experiences. Implying that at best, you only capture eventual change across time in how mass media portray shifts in general kindness or morals).
I would love to ask an expert some questions about the drug guanfacine. Does anyone know whom I might talk to about guanfacine, including Scott Alexander himself if he happens to come across this comment? In terms of what my questions are, I sent the below to one scientist:
I read your excellent paper here (https://www.mdpi.com/2218-273X/11/7/936) and I was wondering if you could help me get answers to some questions that I have about alpha-2A adrenoceptors. There's a lot of fascinating science about these receptors, but I don't know if there's ever been any investigation of why guanfacine (which works through these receptors) would work very well in patients but then later stop working. This is a phenomenon that can occur when ADHD patients. Is the idea simply that these ADHD patients (who experience this phenomenon) have alpha-2A adrenoceptors that are somehow more prone to desensitization (by guanfacine) than is the case for other patients? And then what is the solution to this problem of desensitization? Logically speaking, I presume that increasing the guanfacine dose wouldn't help, since increasing the amount of agonist won't re-sensitize the receptors, will it? So it seems like quite a conundrum. I presume that there isn't any agent that one could introduce that would combat alpha-2A adrenoceptor desensitization.
Incidentally, I saw in one paper that guanfacine (unlike clonidine) doesn't cause (or doesn't necessarily cause) the alpha-2A adrenoceptors to undergo internalization. See here (https://www.sciencedirect.com/science/article/pii/S0021925820583245), where it says that although "significant desensitization of guanfacine-evoked inhibition of Ca2+ currents is detected after 15 min of treatment, ConA blockade of α2AAR internalization had no effect on this desensitization (Fig. 6C), suggesting that guanfacine-induced desensitization does not require α2AAR internalization".
Maybe the reputations of these people make it irrelevant for those who know them, but $100,000 seems like too much for a truth-seeking exercise where judges are employed by the participants. Of course, *I* am too honest to take a bribe, even if the only harm from doing so would be to mess up an internet debate between rich nerds. But if I weren't so principled... there's enough money there that a x% chunk of the winnings would make a big difference in my life.
Is David Burns's "Feeling Good" still the standard DIY CBT book that people (and/or psychiatrists) recommend, or is there something that's supplanted it?
As a non-professional, I liked Burns’ “When Panic Attacks” for anxiety-related issues. It covers the same ground as “Feeling Good,” but much more succinctly. Burns seems to say mostly the same thing in all his books, but keeps learning to say it more clearly.
It also looks there’s a newer book called “Feeling Great.” That may be worth checking out.
Any professors of Economics or Computer Science seeking students graduate students - I have a truly excellent youngster who is looking to enter a PhD program in the USA or Europe. He is currently in Latin America, but in my experience working with him for the past two years (both as data scientist and economist), he's been absolutely top-notch, motivated, and independent.
Please DM me if your department needs a brilliant new PhD student!
“ can you consistently replace “morality” with “kindness/honesty” but otherwise keep the conclusions the same?”
I think at least one place this differs is situations of trade off. “Women and children to the lifeboats” seems like it’s about morality, not kindness; and is also the kind of thing that’s now (at least in theory…) contested.
To a substantial extent, THE cultural problem of our times seems an inability to weigh trade offs because of an unwillingness to accept that they are ever even necessary; and confusions about all morality beyond basic “kindness/honesty” seem to flow from this.
This seems flip but you will see that it explains almost everything!
Including why social scientists/humanists hate economists (the people who keep insisting that everything is trade offs), the fights around covid (a rare case where a new, unfamiliar set of trade offs need to be constructed).
And why talking about AI risk is suddenly so popular (we can do it while ignoring the issue of trade offs and resource limitations. Much more fun than the sad reality of global warming, which has been again relegated to obscurity because, after all, once you have made your climate justice rant, you’re still faced with that uncomfortable reality you do not want to face that, OMG, what if the economists are right and trade offs actually DO have to be made?)
I'm curious if anyone is familiar with simulation software or utilities for the Internet of Things. I'm conducting research on IoT devices interoperability, so I'm searching for simulation software.
But, one thing that strikes me is how many of the comments/blogs about this are saying she was “a bot”. And … I’m not sure they know what a bot is. Certainly there was a person writing the tweets as a fictional character.
Does this point to some deep insight about people’s reactions to AI? Or is it just Elon Musk’s nonsense running off on society?
It's what happens when you give children the printing press. Children are stupid and loud and will scream all the nuance away until all words just mean "good" or "bad". Especially the ones who are invested enough in a troll account to leave a comment.
"I recall two Black applicants we admitted who, in retrospect, puzzle me a bit. One had, like me, grown up middle-class rather than disadvantaged in any salient way. The other, also relatively well-off, had grown up in a different country, entirely separate from the Black American experience. Neither of them expressed interest in studying a race-related subject, and neither went on to do so. I had a hard time detecting how either of them would teach a meaningful lesson in diversity to their peers in the graduate program."
John McWhorter discusses why Affirmative Action is probably not a good thing, and questions what "diversity" even means, which is a question I've been asking for a while. It seems obvious to me (and possibly only me) that we'd much rather have one wealthy white student and one poor white student than a wealthy white student and a wealthy black student. But no, "Diversity!"
I'm very much on your and McWhorter's side on this. But to play devil's advocate: I don't think the claim that privileged Black students individually contribute nothing to diversity, even if 100% accurate, is a sufficient objection to preferentially admitting them. Many mainstream schools of thought re: diversity emphasize creating environments where all students feel included, welcome, and safe. I can easily imagine having more minority students in aggregate would help foster such an environment, even if some of them don't individually bring distinctive personal experiences to the program.
What of the counter that a poor black student might find themselves much more "included, welcome, and safe" with a white person of similar SEC than with a rich Nigerian immigrant? I think it mostly just boils down to Americans being incredibly loathe to acknowledge that class exists at all
Absolutely, I can agree with that; the only objection I care about to preferentially admitting them is that it's blatantly racist. It very well could foster a "feeling safe" environment, but if it takes racism to achieve that possibility, that's unfortunately not an ethically legitimate option.
"The only evil consists instead in the decision to remain in a deficit of existence, to appropriate the power to not-be as a substance and a foundation beyond existence, or rather (and this is the destiny of morality), to regard potentiality itself, which is the most proper mode of human existence, as a fault that must be repressed.
I'd drop the part about evil, but I had a good time at the Philly Rat Fest, a gathering for Critical Rationalism. I don't know why they call it Critical, but I think they've got an interesting take on opening up possibilities.
> Saar Wilf of Rootclaim and ACX commenter BSP9000 have made a $100,000 bet on COVID origins (lab leak vs. natural).
From my reading of the request for judges, they did not actually bet on that, which is a good thing because it seems likely that this question will not be resolved by overwhelming evidence any time soon. Betting on the origins of COVID feels a bit like the Pope and a Chief Rabbi making a bet regarding the divinity of Jesus Christ.
With the universe not being very forthcoming with conclusive evidence, they instead try to bet on which side would win a debate as a proxy. While adversarial debates are widely used to determine questions of fact in legal courts, their reliability is not without fail. If the Pope and a Chief Rabbi were holding a theological debate in front of a panel of theist judges previously non-committed on the question of Jesus divinity, I would suspect that the outcome might be only be weakly correlated with the factual truth, and the losing debater would be unlikely to update their beliefs very much.
Personally, I think a likely outcome is that the lab-leak hypothesis will be assigned a Bayesian probability in the 5%-95% range by the judges after the debate. It is unclear from the text how this would resolve the bet. Will the pot simply be split proportionally to that?
Saar and I tried to do it as a prediction market style bet but couldn't agree on the terms of even how that would resolve.
It's also unclear if the debate will resolve to the correct answer, but I think it could be a useful piece of science communication to get all the best arguments on each side in the same place, see what can be conclusively ruled out, and what uncertainties remain.
Anyways, we got a lot of smart people to apply as judges so it's likely that something will come out of this, and hopefully it's something people find useful and informative.
NHL and NBA are very similar and profitable business models. Yes, they have historical and cultural differences, but if we speak about business, primarily, it's an advertising medium. So the critical factor is the size of the auditory. Why can't we see competition between NHL and NBA for newcomers fans?
Barries to playing basketball are way lower than playing hockey which costs lots of money and needs lots of equipment.
Over time this has reduced the ability for people to develop a cultural affinity for Hockey. This effect is even more stronger among non-white Americans and immigrants which has been the biggest population and economic growth area over the past 50 years.
On top of this is technology. Only in the past 60 years has it been economically feasible to have indoor ice rinks throughout the country and world. Also until HD, watching hockey on TV kind of sucked (and i say this as a hockey fan)
I live in a hockey household, and the One True Sport has gradually ruined all others for me. (Grew up as a classic American generalist sports fan but literally can't even sit still through a football or baseball game anymore.) Your points are spot-on.
The NHL was also a notably short-sighted operation for most of its history; whatever the smart business-strategy choice was, the NHL for decades could be counted upon to do the opposite. That has changed noticeably since the 1990s -- not that the league doesn't still do stupid things but they also now do some smart things. One example is that most NHL franchises now invest in growing and diversifying youth-hockey participation in their markets, with good results e.g. USA Hockey [amateur players and coaches] membership has more than tripled since 1990. That is the way to be building a sustainable fan base but it does take some time.
Totally agree with this. They have definitely turned things around even from the early 2000s. We can just look at how successful Seattle and Las Vegas have been in their short history vs when the Wild and Columbus joined in 2000. Some of that is luck in the expansion drafts (the salary cap helps too), but the league has definitely learned. It always amazes me that the NHL has the most teams of any of the 4 major sports in the US.
The winter classic was of course an amazing idea, I also think they have been doing a good job trying to keep the all star weekend fresh, especially compared to the NBA that can't get any super stars to participate in the dunk contest. Of course the stink of the "Guardians" still hangs in the air, but that can be forgotten about.
I am a Caps fan so the past 15 years have been a roller coaster of highs and lows, but that team is a good example of the impact that youth hockey outreach can have. Helped by the cliff dive that the Redskins/Commanders have done over that time, the continued irrelevance of the Wizards, and the huge growth in the DC market, I think the Caps have done enough to keep interest high even after Ovi retires. The caps have put a lot of money and other resources on youth outreach especially among black kids that will be a key to growing the DC market.
> A lot of the research you build on is likely fabricated.
> There needs to be a revolution in psych research. AI has fucked the current/past supply of research. It is not possible to distinguish.
I think you are referring to the replication crisis? (Which, if I am getting this right, extends far beyond psychology to include ~all the social sciences, and which has also been around for about a decade at this point.)
Um. I am not referring to any particular crisis, I am attempting to make an original contribution to theory that is not grounded in research.
Yes, I do believe that the replication crisis is real, and AI generated content is being planted on the internet all of the time by bots. The research that is being produced automatically on the cloud as we speak is literally indistinguishable from human quality writing. (yes I am human being people are watching me type this HELLO boobobo waga jeebo bobo) (translation: Please don't accuse this of being AI generated because I am smart and a zoomer, thanks). Yes literally all research has this problem it is getting worse as we speak we need to authenticate things and need physical copies that are attached to biiometrically verifiable shit its the only way.
What would be gained by helping anyone to distinguish electronically-generated nonsense from the meat-generated variety? Both kinds are "perfectly good" nonsense, and if the market in fact demands a supply of fresh nonsense, why not use the cheaper one?
Why should meat which egregiously fails the Turing test continue to be employed in churning out verbiage -- rather than in e.g. the field of floor-mopping (or in whatever other tasks that stubbornly resist automation) ?
note: I am at L.H. I know ppl in your community have verified that I am a real person here and typing this. I do not know the extent of what has gone on related to my identity and your community
Affirmative action fell because lots of people not only didn't like it, but noticed that race and ethnicity are protected classes so "no more than X Asians" was a no-no under current civil rights laws. Eventually SCOTUS agreed.
Legacy admissions, lots of people don't like that either, but parental wealth and status aren't protected classes, and I'm not seeing a sound legal argument for telling private universities they can't do that under current law. In theory, you could get Congress to pass a new law saying "not one dime of federal funds to any university that does legacy admissions", but I doubt they're going to want to take that on.
They appear to have noticed that while moderate voters dislike or are ambivalent about affirmative action in admissions, they _really_ dislike legacy admissions. Of course there are fewer and fewer swing-able American voters anymore...but the Dems learned the hard way in 2016 that they can still swing a few key states.
And unlike AA admissions, legacy admissions are also extremely unpopular among both liberals and progressives i.e. the voters who the Dems already have but need to turn out. [I am obviously deploying the word "liberal" here in its modern American-politics meaning.] And those voters are now freshly wound up about the topic due to the SCOTUS banning AA admissions.
So going hard at legacy admissions holds only upsides, politically, for the Democratic Party now. That is the classic situation in which a political party in a tight partisan environment decides to take on a new topic.
Going against legacy admissions isn't going to get them many voters that they don't have already, and it will piss off the elite universities. Since the Democratic Party seems to enjoy having academia on its side, commanding heights of the culture and all that, I'm skeptical they'll make a really big push for this.
They don't need many voters that they don't have already, just some of the dwindling number of swingable voters would make all the different in a bunch of states. And did you notice that GOP Senator (and long-shot POTUS hopeful) Tim Scott immediately came out in support of ending legacy admissions?
In particular attacking legacy admissions is a great high-profile way for the Dems to stop their bleeding among Asian-American voters, and to a lesser degree among well-off Hispanic and Black voters as well.
Academia as in faculty, and politically-active students, will not be put off by attacking legacy admissions, indeed the opposite -- those groups each overwhelmingly dislike legacy admissions. [In a 2019 poll only 4 percent of Dem-leaning students and 7 percent of GOP-leaning students nationally supported legacy admissions.] The only people on the campuses who really want to keep legacy admissions are the administrators and the fundraising staffs, and hardly anyone involved in either party likes those groups of people anymore....the Dems will be going hard after legacy admissions and it will hurt their standing in academia not at all.
Against that, many Democratic legislators and officials and their donors have a vested interest in their kids benefiting from legacy admissions. So that might be a fight worth being seen to have, while also not quite winning. (Or not winning fully-- eliminating legacy admissions from public universities while leaving it in place for private ones, say.)
Well we'll see, but if passing laws that went against their personal interests was a stopper for Dem officials/donors that party wouldn't be serially devoted to things like making income tax rates more "progressive" and defending/increasing estate taxes.
Also legacy admission as a practice was already on the defensive. More than two dozen colleges have eliminated legacy admissions since 2015, mostly publics but also including some high-level private schools like Johns Hopkins and Amherst. Colorado's Dem governor, who has presidential aspirations, has boasted for two years about having banned legacy admissions by public colleges in that state. Democratic state lawmakers in three more states (NY, CT, MA) had (before the recent SCOTUS ruling) introduced similar bills.
And I just learned that U.S. Senator Merkley and Representative Bowman, both Dems, are reintroducing their bill from a year ago to ban legacy admissions by any college/university that receives any form of federal aid or grants. A year ago it failed to attract co-sponsors and hence died in committee. Perhaps an indicator now will be how many co-sponsors the bill attracts and how quickly, i.e. politicians having that "train leaving the station that I need to be on" sensation.
Affirmative action is flawed in design, in that it assumes racism is the reason people are excluded from some things. That can indeed be the case, but isn't always.
I bet it's because they don't like it, not because the industry is keeping women out.
The SCOTUS ruling was along party lines, which is ridiculous. But it does leave open the door for minorities to sue because they were denied admission despite being better credentialed than others who got in.
Does this mean legacy enrollments could be in danger? Somewhat, I must believe, but probably not significantly, since they will be able to make the case that they should be admitted with other arguments. The school is still out to make money, and highly credentialed students who can't afford it may still be excluded, which may benefit lower-priced institutions.
How much money does the expectation of legacy admissions generate via alumni donations? How much do those alumni donations matter from Ivy universities with huge endowments?
Whether Harvard manages to increase its $52 billion endowment doesn't matter much from the point of view of the continuity of Harvard, but it matters for the careers of the hundreds/thousands of people whose job it is to grow that endowment.
Besides, the reason you go to Harvard isn't to mingle with smart people, it's to mingle with rich and well-connected people. If you just want to mingle with smart people you can go to MIT, but you'll probably just wind up as some mid-level software engineer at Amazon instead of President of the United States.
I am tempted to respond with a long diatribe about *separation of powers* and who should be making these decisions. But if the Gray Lady (correctly) concludes that the hoi polloi can’t understand that type of thing, why should I bother?
On the merits: I am hoping that the Ivies determine that the only way to make their « diversity » numbers look good is to cut back on legacy admissions. (Or gridiron football.)
I’m dubious of the claims excerpted below from “An Overview of AI Catastrophic Risks” from Center for AI Safety, which The Zvi describes as a “strong point” with the words: “Pointing out carefully why evolutionary pressures will apply to AIs and that these pressures favor selfish actors and disfavor systems that are altruistic or otherwise positively inclined to humans...”
"The conditions for natural selection apply to AIs. There will be many different AI systems with varying features and capabilities, and competition between them will determine which characteristics become more common. The most successful AIs today are already being used as a basis for their developers’ next generation of models, as well as being imitated by rival companies. Factors determining which AIs propagate the most may include their ability to act autonomously, automate labor, or reduce the chance of their own deactivation.
Natural selection often favors selfish characteristics. Natural selection influences which AIs propagate most widely. From biological systems, we see that natural selection often gives rise to selfish behaviors that promote one’s own genetic information: chimps attack other communities [59], lions engage in infanticide [60], viruses evolve new surface proteins to deceive and bypass defense barriers [61], humans engage in nepotism, some ants enslave others [62], and so on. In the natural world, selfishness often emerges as a dominant strategy; those that prioritize themselves and those similar to them are usually more likely to survive, so these traits become more prevalent."
I’m dubious because selfish genes in biological system “want” to propagate themselves due to the need to run the twin gauntlets of biological death and (usually) sexual selection. Whereas an AI produced by capitalist forces will be naturally selected by humans based on their profitability.
Why, as the paper claims, would economic competition select for the ability of AIs to “reduce the chance of their own deactivation”? Apple doesn’t profit vastly from selling you an iPhone that lasts forever but rather from selling you one that will need to be replaced, so that it may sell you another. Competition by AI providers means constant innovation. Will AIs with selfish* characteristics win out in a competitive marketplace?
Maybe but my intuition is that the marketplace would select against AI selfishness. (Unlike humans, the AI isn’t trying to fuck anyone.) AI evolution seems likely to be a process of domestication, since they will be bred for human use.
* We should make a clear distinction here between “selfish” and “manipulative” because taken to the nth degree their meanings pull wide apart.
An AI sold to the consumer as a commodity might want to be time-limited (probably via it being a subscription service), but one put in charge of eg. making the chip factory more efficient is a quite different proposition - you'd want it to as part of its job protect against nefarious forces opposed to efficiency, like, say, worker's unions agitating against AI replacing human jobs....
Seems like a valid point to me. So long as AI is designed and manufactured by human organizations, the relevant selfishness will be that of the companies, not that of the AI's. On the other hand, it could be that crooks, perhaps using other AI's, would hack AI's and demand ransom to reactivate them. Or enemy nations could do it. Under those circumstances we'd expect the companies producing AI's to make them hard to deactivate.
A related possibility would be that whatever system keeps the AI aligned would also be a point of particular vulnerability. People could attack the AI by activating whatever saftety mechanism was supposed to disable the AI if it became harmful to humans. Or of course an enemy nation X could hack into the AI and change its alignment so that it is only aligned with the wellbeing of nation X, rather than with the wellbeing of humanity. So then the selfish interests of companies making AI motivate them to weaken the alignment mechanism, so that the AI was less vulnerable. Of course they wouldn't say, hey we've weakened alignment. They'd say, our new alignment system is 70% less vulnerable to corruption.
In 2021, 10,000 Canadians opted for assisted suicide. There are people that believe this is immoral. I know It goes against Catholic teaching but I don’t know if other religions think it is a sin.
But II wonder - are there.people who believe capital punishment is just, but assisted suicide for suffering terminal patients is unacceptable?
The devil is in the details. I'm in favor of capital punishment, and expect that it would happen after extensive trials ladden with proofs, testimonies and defense of the would-be condemned. I don't expect euthanasia to be so well-guarded.
Consider this: the USA, over 300 million people, one of the most violent western country, is executing less than 20 people per year. Canada's population is almost 1/10th of the US, and euthanize 500 times more.
Then there's the anecdotes I got from friends that worked in retirement homes & elderly care. I don't care half of the coworkers they depict in their story to not put me to death just because it's convenient to them.
I think it is a consistent if you you postulate a theology in which suicide is a grave sin.
Under that postulate, assisted suicide is assisting the patient to damn themselves, which would be bad. By contrast, executing a criminal would not burden them with a sin on their part because you do not exactly seek their consent beforehand.
(Killing patients without their consent would be the preferable as far as the consequentialist outcome for the patient is considered, but it is probably ill-advised to mix theories of ethics in that way. One might possibly rig such a system by prescribing the death penalty for stating the heretical opinion that one does not want to continue living, but I don't think anyone has ever tried to implement assisted suicide using that workaround.)
I think the support for the death penalty is kind of grandfathered in most value systems which were state-supporting in the pre-modern era. Before the economic surplus of industrialization supported long term imprisonment, there were only so many things you could do with your more criminals, mostly enslavement, exile, torture, maiming, and execution. Anyone sharing my sentiment that all of these options are mostly horrible was likely not having a hand in writing state-affirming ideology.
I've heard it argued that assisted suicide is corrupting to the medical profession. You don't need medical personal to execute a person by firing squad, hanging or gas chamber.
An alternative to assisted suicide is refusing liquids and nutrition which is just about universally accepted for terminal patients, is minimally painful in a palliative care setting and death occurs a few days or at least terminal unconscious.
Lots of other people, too, I’m sure. In fact this seems like normal default morality to me (even though I know intellectually that there are people in all the other quadrants). It’s bubble effects for us both all the way down.
(FWIW I’m not sure about capital punishment as a public policy proposal in the West in 2023 for various reasons, but the OP asked about its justice, and I have no problem with that.)
Just so I understand, you are against physician assisted suicide but not saying that a person deciding to end their own life is immoral, right? Or do you mean something else?
Now I’m think of the likely apocryphal story of the suicidal Catholic who publicly murdered someone so he could confess and be absolved of his sin before he was hanged.
And I'm reminded of Unsong, where it is discussed how there is more rejoicing in heaven over one sinner repenting than 99 righteous people. So go ahead and murder, and sincerely repent, is the message?
I'd say sincere repentance is a hard sell when deathbed repentance was part of your plan from the start - you'd have to repent from your plan to selfishly repent, while still repenting. But I wouldn't want to make that argument in a thread invoking "Unsong", because, you know, That Guy.
I see the best arguments against euthanasia as being Schelling fencey... there's a slippery slope from "fine, you can die voluntarily under exceptional circumstances" to "ehh let's just kill off all the tricky patients to save money". I've heard anecdotes that Canada is slipping down this slope pretty fast, though I don't know how accurate they are.
The death penalty is less of a slippery slope because we're reasonably confident that introducing the death penalty for horrible murder cases won't eventually lead to it being used for speeding tickets.
So I can see why someone could reasonably support the latter but not the former. Keep euthansia behind a Schelling fence, but allow the death penalty because we have experience with it and know it doesn't screw things up too badly.
The slippery slope in the death penalty is from people who have definitely committed horrible murders to people who have probably committed horrible murders to black people who have been credibly accused of murdering white people.
The assisted suicide laws that I know of allow a physician to prescribe a lethal dose of a drug. The patient then takes the drug at home. It may also allow people to go to an assisted suicide facility like those in Switzerland, and ask to be given the drug via IV. So long as assisted suicide is carried out that way, I don't see how it can slide down the slope towards doctors electing to euthanize patients they think would be better off dead.
I assumed that most of it was the benefit of much smaller class sizes - it's well accepted the 1 on 1 tuition gets you at least 2 SD over standard western schooling (it's just fundamentally a luxury until we get much better AI)
Saner sleep schedules sure as hell can't hurt though, and probably does contribute meaningfully!
When I was homeschooling my daughter we both slept til around 10 am most days. Other homeschooling families were the same. The kids slept til they woke up naturally. Of course, there are so many differences between schooling and homeschooling and between parents who choose school and parents who choose homeschooling that I don't know how you'd ever figure out what differences count most.
Can anyone point me to what they would consider an unbiased, up to date summary of the evidence for *and* against either of the 2 following statements? Hoping for something that tries, in good faith, to present the best evidence for both sides. Needs to be something a layperson can parse.
-It is unlikely the covid pandemic started with a lab leak.
-Mask mandates and/or "lockdowns" saved a lot of lives during the pandemic
On the lab leak hypothesis, my recommendation is not as strong, but I commented earlier in this thread that I tried to get ChatGPT to do a proper Bayesian analysis of the probabilities. TL;DR is that while you can't really trust ChatGPT 3.5 to do the math; the WHO and several reputable journals reported that:
- For the most-closely-related deadly MERS and SARS viruses, human blood samples stored before those outbreaks showed that a substantial fraction of people in those areas had developed antibodies to those viruses before the known outbreaks, because the viruses were gradually crossing over into humans as they adapted, and before they could transmit from human to human. At least a few thousand human blood samples were similarly tested from in the Wuhan area that were stored just before the COVID outbreak, and none showed antibodies. The Bayesian analysis would seem to indicate that the likelihood of natural "seroconversion" or gradual adaptation to human transmission being completely absent in the case of COVID-19 is extremely unlikely.
- Likewise, though I didn't mention this in the earlier post, in the cases on MERS and SARS, a relatively small number of animals (hundreds to a few thousand) were tested before finding the intermediate species. Something like 80,000 animals were tested for COVID-19 and no intermediate species has yet been found. Given the numbers, the Bayesian analysis suggests that the likelihood that an an intermediate species exists is vanishingly small.
Again, take with a grain of salt and if possible, run your own numbers. I wish I could find a real study on this. I tried with GPT-3.5 and was frustrated by the hallucinated data; however, I confirmed enough to believe that the overall conclusions are basically valid. I hope to make time to post links to the original papers and do a proper Bayesian analysis, but haven't found the time so far. The most interesting source I've found so far is obviously politically biased but seems to have some legitimate source links, I still need to OCR or manually transcribe.
For an evenhanded analysis of the effects of COVID mask mandates and lockdowns, I can strongly recommend https://maximumtruth.substack.com/p/the-covid-fudge-factor. This guy is a Data Scientist who came up with the apparently (and surprisingly) novel approach of examining the official "excess deaths" by country and U.S. state rather than official COVID numbers; these numbers are much harder to "fudge" for various reasons. The results show (surprise!) that both major political factions in the U.S. made a bit of a hash of it.
Read as far as his first attribution of an action to "the media"--which fortunately occurred in the very first paragraph--and decided that there was very little chance that reading further would reward the time or effort. I hope I didn't make the wrong decision, but I doubt that I did.
Maxim is right leaning, I think he even has a job at Fox News, but I've found his numbers are consistently accurate in all his covid and vaccine articles.
beowulf888, who sometimes posts here, used the pandemic to become quite smart about covid. He's objective and fair-minded. I'd recommend asking him on Twitter. He takes DM's.
In your review of ‘The Body Keeps the Score’ you described one patient who had seemingly been ‘cured’ of severe trauma by reading the book.
You wrote: “[Update, written a few weeks after the rest of this post: maybe it is all wizardry. I recommended this book to a severely traumatized patient of mine, who had not benefited from years of conventional treatment, and who wanted to know more about their condition. The next week the patient came in, claiming to be completely cured, and displaying behaviors consistent with this. They did not use any of the techniques in this book, but said that reading the book helped them figure out an indescribable mental motion they could take to resolve their trauma, and that after taking this mental motion their problems were gone. I’m not sure what to think of this or how much I should revise the negative opinion of this book which I formed before this event.]”
Are you able to update on whether that patient’s recovery was permanent/long-lasting?
“For example, the Biblical Abraham would famously feed and host any guest who came to his door, which is better than most modern people. But also, he kept slaves, had a child with one of them, and then agreed to his jealous wife’s demand to send the slave-woman and child out into the desert to die.”
What’s a $10 word for judging the morality of a person of a foreign culture and different time period? I do this too, being human, and I think it’s useful as *A* perspective. I’m not saying any moral or religious ‘hero’ was faultless in their actions. See the Torah or New Testament(with arguably one exception). Were the Vikings wrong for leave a malformed or smallish child exposed on a mountaintop – or in their primitive society was it a mercy?
The $10 term you're looking for is probably "Presentism", which specifically refers to the historiographical sin of assuming present-day morality and cultural values to be objectively correct and framing and interpreting the past by primary or exclusive reference to those.
There are a variety of reasons this tends to be disfavored, but one of the big ones is that presentists judgements tend to serve as what LessWrong readers call "semantic stopsigns". For example, judging leading Confederate politicians to be evil slaveholders is a very tempting judgement, since they were generally slaveholders, extensive evidence exists for the conclusion that preserving the institution of slavery was the dominant and central motivation for secession, and since slavery in general and chattel slavery as practiced in the antebellum/perbellum South was egregiously evil by modern standards. But such a judgement tends to obscure useful analysis into the cultural, political, and personal motivations for secession and for various decisions made in forming and leading the Confederacy.
Another big reason for avoiding Presentism in historical analysis is that it blends into the "Whig History" fallacy, in which the present is seen as a golden age and the rest of history as a steady climb out of barbarism towards that golden age. That the past sucked because people in the past were various combinations of evil and foolish; but as Chesterton observed, if our forefathers were fools, then folly appears to be a hereditary disease. You can definitely make a case for the present being better, but that should be viewed as a hypothesis to be analyzed and not as axiomatic truth. Institutions and values of the past, even where they're radically at odds with modern standards, often make a great deal of sense in the context of the times and places where they arose and dismissing them as barbarous cuts off useful analysis as to why they arose and were retained as long as they were. And change over the ages has not even been approximately linear towards present outcomes, and moreover, it's often been the case that changes towards present institutions and values (automatically assumed to be "progress" by Whig History analysis) have had severely negative consequences in the medium term that should not be overlooked.
>Would you care to offer your opinion about how much the Industrial Revolution influenced the end of slavery in the US versus moral considerations?
A fair amount, probably, in a few different respects.
The obvious one is that differences in industrialization patterns were a major factor in the Union winning the Civil War. The Northeast industrialized directly, and the industrialization of the Northeast helped drive the spread of yeoman-agriculture oriented settlement of the Old Northwest (modern Midwest) by serving as a market for harvest, a local source of farm equipment, and an economic based with which to build the canals and railways that linked the Northeast and Northwest. Meanwhile, the Deep South got hit with something like the "resource curse" as demand from British textile mills drove the economy even more towards cash-crop plantation agriculture growing cotton (and to a much lesser extent, indigo for dye, plus sugar and rice for the luxury food market). Wheat and factories make for a much better economic base for war-making than does cotton and indigo, giving the North a big advantage out of the gate. Furthermore, industrial/commercial cities and a yeoman-agriculture hinterland, with a great deal of economic opportunity in both regions, pulled a lot of immigration to the North, while the slave/planter social order in the South actively repulsed European immigrants, so the North had a much larger population (even bigger if you only count free citizens) from which to recruit their soldiers.
In terms of the short-to-medium-term lead-up to the war, industrialization played a key role in the North becoming politically and economically dominant. More people means more votes for President and the House, and the expansion of yeoman settlement drove the admission of more free states to tip the balance in the Senate. And the split in economic models helped lead to the parties realigning on sectional grounds. Once that happened, a pre-existing difference in moral values kicked in, as the Puritan/Quaker dominated culture of the North was much more hostile to the idea of slavery than the Cavalier-dominated culture of the South's political classes. This was reinforced by economic considerations, as most Northern states either never had institutionalized slavery or abolished it at the state level relatively early in the Antebellum period, while Southern planters viewed their wealth and status as resting on a foundation of slave labor.
Economic factors leading out of the Industrial Revolution also helped reinforce the concentration of slavery in the Deep South and its abolition in the North, as cotton planters bid up the price of slaves well past the point where it made economic sense to buy or keep slaves to grow wheat or corn, and even the tobacco grown in much of the middle and border south (especially Maryland and Virginia) was becoming an economically marginal use of slave labor. So the economic incentive for Northern slaveowners in the early 1800s was to sell their slaves down the river, and while many Northerners didn't want to do that for moral reasons, those who thought that way were more likely to either never own slaves in the first place or to just manumit any slaves that they somehow acquired.
I had read previously and it made sense that there was a lot of push from industrialization and some pull from prevailing morality as you wrote. You added additional economic pressures I was unaware of as well as other interesting details. I've picked up Lincoln(D.H Donald,1995) again(maybe I'll finish it this time!) where I vaguely remember pre-civil war there was discussion about shipping slaves back to their origin(most of the indentured reportedly didn't want this) and also considered was enslaving poor whites *for their own good*.
History is never quite (or at all) what we think at first.
Appreciate the reply Eric. You've given me more to research and think about.
>I vaguely remember pre-civil war there was discussion about shipping slaves back to their origin(most of the indentured reportedly didn't want this) and also considered was enslaving poor whites *for their own good*.
Pushing freedmen to move to colonies in West Africa was definitely a thing. My understanding is that there were three main threads of logic behind the colonization movement: basic racial separatism, an attempt to sidestep social fallout from emancipation, and an attempt by abolitionists to mitigate some Southern objections to gradual compensated emancipation. Several colonies were founded and thousands of freedmen transported thither. The colonies declared independence as the Republic of Liberia in 1847 and were recognized by Britain in 1848 and by the US in 1862.
Enslaving poor whites was never a serious proposal, as far as I know. The closest I'm aware of is rhetorical flourishes by some apologists for slavery in the late antebellum period who argued that in some ways slaves were better off than the poorest free laborers.
>Appreciate the reply Eric. You've given me more to research and think about.
My pleasure! If you're looking for additional reading material on the culture, politics, and economics of slavery, secession, and abolitionism, I highly recommend William Freehling's two-volume work "The Road to Disunion".
"mostly about kindness-and-honesty, whereas other people interpret “morality” more broadly to include things like self-control)"
Yes, “self-control” which is ALL the virtues. Our *intention* is the morality of our actions.
- - -
"Strictly speaking, there are no such things as good and bad impulses. Think once again of a piano. It has not got two kinds of notes on it, the "right" notes and the "wrong" ones. Every single note is right at one time and wrong at another. The Moral Law is not any one instinct or any set of instincts: it is something which makes a kind of tune (the tune we call goodness or right conduct) by directing the instincts.
… [Re: “kindness-and-honesty “]
By the way, this point is of great practical consequence. The most dangerous thing you can do is to take any one impulse of your own nature and set it up as the thing you ought to follow at all costs. There is not one of them which will not make us into devils if we set it up as an absolute guide. You might think love of humanity in general was safe, but it is not. If you leave out justice you will find yourself breaking agreements and faking evidence in trials "for the sake of humanity," and become in the end a cruel and treacherous man.”
We consider such people to be psychopaths, meaning that there is something wrong with them. Their natural impulses are severely distorted.
On the other hand, there are impulses that would lead someone to desire killing another, and to enjoy it even, that would be good impulses in a different situation. The impulse to inflict violence on others can be good if you are a soldier fighting in a just war, or a rebel attempting to throw off injustice, or if you are fighting for your life in self defense or in the defense of others. The impulse to dominate others is the kind of musical note that it is hard to find a place for in most music, but it too can have it's place in the form of ambition to succeed in lawful arenas, such as sports or business.
"here are impulses that would lead someone to desire killing another, and to enjoy it even, that would be good impulses in a different situation."
Perhaps you mean useful impulses rather than "good"?
- - -
"Several paramilitaries in battle fatigues armed with automatic weapons – some speaking Arabic in distinctive Lebanese accents – pull wounded men out of the back of a van and drop them on to the ground, then shoot them in their heads at point-blank range.
As they shoot their victims, some of the paramilitaries seem almost giddy with excitement.
A man who appears to be their commander admonishes his men, “Come on guys, we are here to carry out our duties not to seek revenge on our own. This is unacceptable.”
One of the paramilitaries smilingly replies, “But we are killing them in God’s cause, only in God’s cause.”
The wounded men lying on the ground awaiting their deaths repeat religious phrases that are commonly said just before death. They all appear to be civilians.”
Methinks the author meant *basic* impulses(why do serial killers..?)
He believes in a Natural Order based on "Moral Law" and my take is that applying that Law (or not) to our thinking and actions is what 'life, the universe and everything' is all about. : )
"Our whole life is startlingly moral. There is never an instant's truce between virtue and vice”
I saw the new Indiana Jones movie. It was perfectly fine, but I honestly suspect I'll struggle to remember much about the film except the last 20 minutes or so a year from now. I seem to be unusual among internet commenters in that I liked and still like "Crystal Skull", but even if you don't it's still memorable - people still have arguments about it fifteen years later.
It came out the same year as the first "Iron Man" film, which is tied with the 2001 Spider-Man movie for Film With the Largest Impact On the Theatrical Film Business of the past 23 years. That "Iron Man" film basically kickstarted the entire Marvel Cinematic Universe, but the 2001 Spider-Man film may have made that film possible in the first place.
> I liked and still like "Crystal Skull", but even if you don't it's still memorable - people still have arguments about it fifteen years later.
Aha! An opening for me to propound my headcanon that Indy surviving the nuke had nothing to do with the infamous lead-lined fridge. The real reason he survived is that he drank from the Holy Grail in the previous movie, which warded him against the effects of hellfire.
I think the first Spiderman with Tobey McGuire and Kirsten Dunst was about as good as it could have possibly been made. Absolutely true to the spirit of the early Spiderman comics.
For point 2, it seems a very weak point if that’s what they mean. To me it is like the situation with fish getting smaller. 150 years ago men with hand woven rope nets on wind powered wooden vessels were able to toss their nets of the side and routinely harvest very large fish over 1 metre in length to readily feed their people. Today you have fishermen with ocean floor scraping nets chasing fish by radar to get much smaller fish less consistently. Yet each one’s lifetime is too short to see the change other than in old fisherman’s stories and photos from 100 years ago.
This is well known, agreed upon fact, and the decline of mature and abundant fisheries is a huge topic with multiple major conservation organisations and charities working in this area. And this social scientist shows up with the equivalent of a study saying the average mid career fisherman thinks his experiences with fish size are pretty even so far in his life, in fact we have over 50 years of ‘data’ from such mid career fishermen who have reported evenly sized fish so far in their experiences….so what? What a needless and unhelpful pedantic point to make. Moral decline and its more important impact of civilisation decline are what matters, not this blind over emphasis on individual feelings.
Re Saar Wilf and BSP9000 and the COVID lab leak bet, I'd be interested in being a judge.
My qualifications: I don't want to put my whole life story here, but I have a BS in physics and an MS in bioinformatics. I've worked in genomics for 10 years on the computational side. Mostly in cancer, but a substantial amount in infectious disease (though very little virology). Happy to provide a lot more detail in private.
My biases: Generally I have always been skeptical of the lab leak hypothesis, but I always thought it was plausible enough to be worth investigating. I have not done any significant amount of research on the topic.
I tried to respond to everyone who posted there, got conversations going with many of the applicants, and I scheduled interviews with some candidates already. So, might be too late, might not, but you're welcome to talk more if you want to be considered.
I would also be interested in being a judge. Long time SSC/ACX community member. I have a phd in computer science, in the area of economics and computation, so I'm a broad multidisciplinary thinker. I bet on prediction markets and generally have a lot of curiosity about how the world works. This translates to me de facto having 5% of a degree in many, many fields.
Potential biases: I'm a "mild" covid skeptic in the sense of disagreeing with much of the enacted covid policies, etc. and thus believe media reporting is biased in all things covid related. I have a relatively high prior on the lab leak hypothesis just from base rates (i.e., quick and dirty "outside perspective" estimates). Have argued about this online, but essentially only defending the "it's obviously plausible" side rather than an actual yes answer.
Compensation: $100/hour
Not creating another online account for a low chance thing, ask Scott for my email or provide an email address here if interested in talking more.
I'd be grateful for any stray tips anyone might be willing to offer on getting an entry level job as a webdev (MERN/MySQL and a few trimmings) bootcamp grad. I have some hobbyist-level knowledge of C from back in the day, too, but no experience/cert to show for it.
I'm one of those middle-aged guys who actually 'learned to code' after a decade-stale STEM undergrad and lot of drifting (gotten some good advice about that in a thread here a couple of years ago) and graduated with my first and only credential right into the teeth of the post-pandemic industry glut-and-churn.
This is, as the good hound says, fine. No complaining here. I get that major constraints exist on my potential. I'd just like to do my best to maximize what there is of it. Should I shotgun the postings? Should I bother about a salary floor? (thankfully I'm single and used to living very frugally) Should I give up for a year and drive a truck? (I'd prefer not to. The clock is ticking as it is, and I actually like programming as an activity. If anything, before the sun sets on me for good, I'd like to pivot more into backend and more concept-heavy areas, perhaps even ML. Visual design/UX isn't really my forte.) Anything I should avoid or try to seize on?
After the first job it will get easier (unless AI eats our jobs soon), so you don't need to find perfect, just find something you can endure for one year.
> Should I shotgun the postings?
This probably differs in various countries, but where I live, you can simply approach a job agency (or more of them), give them your CV, and they will call you.
> Should I bother about a salary floor?
Partially. It helps if you can figure out what is the junior salary in your area. If someone offers much less, it is a red flag. (Naively, one might expect that if they pay you less, they will in turn require less from you. It doesn't work like that. If they pay less than others, they are either insolvent or greedy, either is a bad sign.) But the important perspective is long-term; your salary can increase significantly after you change your job later.
> Should I give up for a year and drive a truck?
A bad IT job is still an IT job on your CV, and brings you one step closer to being a senior (i.e. better paid) developer.
The job agency path does exist here (eastern Canada) but from what I hear from my peers the influx of experienced people into the market has placed bootcamp FNGs like us pretty firmly on the shelf as far as the agencies are concerned. I'm registered with a couple but doubt I can bank on them.
Yes, I've been reading the discussion here on the odd hiring pattern in the tech industry (somehow break in, prove you can do the job, then leave and look for the real job). It makes me wonder what's in it for the companies that serve as the one-year incubators of what must be from their perspective barely competent coders. Still, I'll take the advice on avoiding the rock bottom red flags despite my hope that bad pay will mean less competition.
Thanks for responding. By the way, do you ever intend to resume writing about Java game programming?
> what's in it for the companies that serve as the one-year incubators of what must be from their perspective barely competent coders
There are different opinions, but it seems that hiring juniors is like buying lottery tickets. You hope to find someone who becomes a superstar in a year, and who is very averse to changing jobs. (Such people actually exist.) If you succeed, then you have a great coder who is also cheap and dependable. Finding one such person may be worth spending money on dozen juniors who either never become good, or will quit soon afterwards.
(That assumes that the choice is rational. It is also possible that managers simply underestimate the difference between good and bad coders, and are happy that the barely competent ones accept lower salaries.)
> do you ever intend to resume writing about Java game programming?
Oh, you are one of the four readers, thank you! Sorry for the long delay. I got emotionally stuck in a quite stupid situation: the next game is done, but I was hoping to also include a (very simple) level editor. The level editor turned out to be more work than I expected. Rationally, I should cut my losses, publish the game *without* the editor, and move on. Instead, I procrastinated for months. :( It is obvious what is the right thing to do, I just need to actually do it. Thank you for reminding me!
Stray tip, find stuff you like (cos, projects, software, paradigms, etc) and dm people legit questions or thoughts, have fun, keep coding, and let people know you're looking for work.
If you're not getting interviews, then definitely shotgun the postings. (As in, several hundred applications. You should allocate several hours a day to applying for jobs). You should also get your resume reviewed (either by people you know or online)
Thanks for the advice. I've gotten the resume looked at by the bootcamp folks, who have pronounced it Good (though unavoidably weighed down by inexperience/employment gap). Re: applications, I've been treading a middle path so far, meaning I've spent more time researching companies and postings that fit my limited credentials extra-well and writing bespoke cover letters than actually applying. Maybe I'll tilt that stick in the direction of quantity as you suggest.
I do have LinkedIn, yes. Appreciate the advice on maximizing "follower count".
I take your point about padding. Not super comfortable with it but I'll do a dive into what is and isn't close enough to my bootcamp techs. Writing queries and logic in slightly different idioms of SQL is a very good example.
Thanks for taking the time to reply and for the words of encouragement.
Regarding trying to quantify morality, I've heard that the murder rate is flawed; it's said that improved emergency medicine allows a signicantly higher percentage of people who suffer knife or gunshot wounds to survive. Incidence of ciolent attacks is said to be more reliable.
I wonder about the rate of blood donations, controlling for mostly stricter screening over the past few decades.
A place where donors have been, and remain, unpaid, would remove one confounding factor.
Hitting 200% improvement in the past 30 years strikes me as high, but not implausibly so. For "public" murders, we have a large number of changes in how trauma management is done which could add up to this. This includes cell phones for prompt dispatch, hospital trauma specializations and notifications, ITLS/PHTLS/ATLS trauma protocols, hemostatic agents, tourniquets, TXA, and I/O access devices. These all add up to significant improvements in outcomes, even if they don't address "hidden" domestic murders.
On a raw numbers perspective, the case fatality rates for stab wounds has declined a bit (hard to say exactly how much because of noisy data and very low rate throughout the time period), the CFR for single gunshot wounds has declined by about a third, and the CFR for multiple gunshot wounds has increased by about a quarter.
On a multivariate "odds ratio" analysis taking into account demographics and various indicators of injury severity in individual case reports, the odds of dying from particular injury have declined by about half for stab wounds (0.53 odds ratio with CI 0.4-0.8) and by about 2/3 for single gunshot wounds (0.35 odds ratio with CI 0.3-0.4), but held roughly steady for multiple gunshots (1.05 odds ratio with CI 0.8-1.3).
Mild pushback against the implausibility of that idea; in the UK at least, we probably have got much better (as a health system, rather than necessarily at individuals) at treating traumatic injuries, although this is pretty location-dependent.
I just watched an episode of the show "Hoarders" where the crew cleaned out a house where one part of the floor had several years' worth of dog feces and urine caked on it. They had to use shovels to scrape it out, and the workers wore biohazard suits and gas masks.
Everyone who went inside the house complained about its intensely bad odor. But aside from smelling gross, was the air in the house an actual threat to the health of the people who went inside? Do bacteria from the layers of dog waste on the floor somehow float up into the air, get breathed into the noses of the humans, and cause them to get sinus and lung infections? In such a place, what would be the mechanism of infection?
Urine and to a lesser extent feces has ammonia in it. Without proper ventilation this can cause health problems. In fact there is another episode of hoarders where a number of cats had to be euthanized because of disease brought on by the level of ammonia in the air. They didn't say what the disease was, this was just a quick comment from the vet they had at the site.
Others have mentioned that the bacteria and feces can easily become airborne. Mold can as well. The urine and feces will increase moisture in the air and on the floor which will make it a better place for mold to grow. High levels of mold can cause a lot of respiratory problems.
The air in the house was probably fine before anyone started work, I don't want to imagine the smell and it was probably a long grade health hazard, but it wouldn't kill anyone. After the work started though...
Well, at the very minimum it would have kicked up a hell of a lot of dust. Any solid particulates that get in your lungs have a tendency to remain there and over the course of a career this can add up to some pretty major conditions. Add to that that this dust is formed of dry fecal matter and all it's assorted bacteria, fungi and parasites, and you'll begin to understand how little anyone would want that on their clothes or in their bodies. A proper mask and protective clothing would definitely be the preference.
Fecal matter contains a lot of bacteria and fungi, many of which can probably survive in some sort of dormant state for a long time. All of them can live in at least one biological system or at least one mammal. If any of them are somewhat unexpected for a human microbiome, but manage to survive, or displace something relevant, then they could probably cause some sort of illness.
Urine tends not to have any sort of living cells in it.
Viruses are very unlikely to be relevant in anything that hasn’t contacted a living animal in the past day or so.
Without looking anything up, I know that Hantavirus is spread when people breathe in disturbed mouse droppings. So maybe there are similar viruses in other animals, though I bet pets are less likely to be infected. On the other hand, pets of hoarders might experience a bit of neglect...
The hazmat suits and gas masks could also have been required just to protect people from the smell. I can imagine that smelling bad enough that it's impossible to work without substantial protection.
I think about that sometimes when I clean out the cat's litter box, because litter is sort of dusty, and I'm sure I inhale some of the dust. On the other hand, people sprinkle bone meal, blood meal and manure, all of which come as powders, onto their gardens. And I'm not sure whether dog waste is better food for bacteria than all the organic matter in people's garbage can's and compost piles, or the apples rotting under the apple trees, cut grass on lawns, dead leaves, etc.
I'm not any kind of expert, but dried faeces can powder quite easily, and if disturbed would drift readily on the air – either to be inhaled or to settle on surfaces and be transmitted by touch.
I could imagine that such an environment might also be conducive to the growth of mould and fungus, the spores of which can be toxic and carcinogenic if breathed in.
Any advice on how to mentally get more interested/invested in sports? Especially let's say baseball. I'd like to cultivate an enjoyment for its own sake but also be better at sports-related small talk.
I'm pretty stereotypically male-brained in most ways but sports have just never clicked for me. How do people remember a zillion statistics and players (maybe people wonder how/why I remember financial market data or history facts)? Why do you feel entertained and invested in the outcome of regular season game #67 out of 150-something? Does game after game, season after season not start to get repetitive and tedious? How do you have time for all this? Jerry Seinfeld had a bit about how players and teams are always moving around; you're really just rooting for the jerseys.
I like going to live games but the actual outcome is whatever unless it's a particularly dramatic game. I got somewhat into football for a few years but have mostly lost interest.
The question is of the mental aspect. You remember financial or historical facts because you understand them and their implications, and you find the subject interesting in some way.
Speaking as someone also not into team sports, I can understand, at least, how some people are. For example, batting average is a statistic in baseball. If you memorize the batting average of every player in the league, that's tough because it is associating a number with a player, and neither means anything. But if you learn which player has the highest batting average, and see them play and note they don't get a hit when they are at bat and realize the effect that will have on their batting average and think they will surely get a hit the next time they are at bat, unless the pitcher they are up against has some technique they use which that particular player find hard to deal with. Yet they have the highest batting average for a reason.
And then there are players with low batting averages. They are playing professional sports, so must have some aspect that makes them extremely good at the sport in some other way, or perhaps their batting average will increase with experience. Once you understand the underlying mechanisms for the statistics then you may find them more interesting.
And then there are the surprises, which I think all sports fans live for. Your team is losing, but something happens, like an unexpected home run, which evens the score or puts your team in the lead. For this, you have to already understand the game and like a particular team, so you would already have the mental interest.
I've played sports since I was a kid, but never cared to watch, except playoff games occasionally.
The draw for viewers might be in its capacity as a social activity (rambling about players and teams seems to be a serious pastime), to engage with tribalism (maybe?), for the chaos/unpredictability of high-stakes games which creates a kind of drama, for gambling, and/or nerding out about stats.
I never felt invested in a team, but I appreciated seeing a "good game", high intensity. I never cared about players or stats, and I never found conversation surrounding sports to be interesting. Having the game on tv reduced to what it is, then, it's mostly boring (with some sports, obscenely so, and I've read multiple anecdotes of baseball fans who say they like it that way because, no joke, they "barely have to pay attention" and it's "relaxing", like it just happens to be there).
I suspect in part, like all tv, it's a device that gives people social permission to "do nothing", drink beer and sit there with or without a friend. And "not think". I don't need sports on tv to do that.
For E-sports, at least, I find it best to find a good commentator. A game may be esoteric and weird, but a solid host should be able to convey the broad sweep of events for the layman, the emotional keys for the invested, and break down the mechanics of what's on the screen for those who want to learn more. Not sure how well that scans to traditionally sports, but it's always been what worked for me.
It also helps if your goal is a bit more concrete than "be better at sports-related small talk". For instance, I wasn't into sports growing up, but then I lucked into a small group of smart quantitative-leaning friends with wide interests who almost all happened to be interested in sports for its own sake. Spending time with them gave me a pretty clear 'why' for cultivating interest in sports, and also clear feedback, in the form of how well I was participating in sports talk with them (with the million little hard-to-legibilize specifics that entails).
Ugh, why? Professional sports are an absurd waste of time.
But if you must, join a fantasy league with friends. There's usually daily email/text chatter full of typical male-bonding-type behavior: shit-talking, ball-busting etc. The social dynamics might make it fun for you until you know enough about the sport to care about it directly.
1) Learn more about individual players. These guys are all humans with their own stories. Learning a bit about them and coming to like them will make you want to cheer their successes.
Documentaries are often good in this regard - "Welcome to Wrexham" (English football) or "Making Their Mark" (Australian football) are two I'd recommend.
2) Get involved in some sort of sports prediction competition. This could be a tipping competition, betting, fantasy, whatever. You will get by far the most value out of this if you're doing it with other people you know and can talk to.
3) Play a sport yourself. Bonus points if you track your own stats.
When I was younger, baseball cards probably helped create interest in the statistics of the game. As an adult, fantasy football made me much more interested in football stats/players.
I've found that when I do a sport even a little bit, I become much more interested in watching experts do it. I think it's because I've learned how hard it is to do the crucial parts of the sport really well, so seeing people who can do it is fascinating.
I enjoy a well-written sports book, but don't watch sports on TV, and seldom attend an event in person. The ticket prices tend to be outrageous, and the noise level and drinking are off-putting. Basically, I always feel like an outsider at games.
Baseball particularly lends itself to feel-good movies, which I really enjoy.
Earlier this year a sports friend gifted me a one-month subscription to JoeBlogs on Substack, and the writer, Joe Posnaski is a good enough writer that I enjoyed his posts. I was/am not enough of a sports guy to pay to extend my subscription. I am on the free mailing list, and receive truncated articles which are still pretty good.
I used to get Sports Illustrated 3rd-hand, and loved the writing. The human-interest stories were often excellent.
In general I've found my sports friends to be mechanically disinclined. I don't know that this is a fair generalization.
Not a joke. I'm very lucky in this respect in that I can make myself be highly interested in the result of a $5 bet, and it's recently legal in my state. Just don't go nuts (easy to say, right?)
Haven't watched baseball since shortly after the Mariners had their record-tying year back in 2001. They got Ichiro Suzuki that year, a star Japanese player, who treated every run like it was important. I remember him in a rundown one game, still running back and forth as hard as he could, and my dad shouting at the TV for Ichiro to give up because he was going to hurt himself if he kept trying to juke the rundown, but that's the energy that makes things exciting.
They also had a game that year where they went up twelve (12!!) runs in the first three innings, and then LOST. Unbelievable.
An old Pittsburgh Steelers football game had a hell of a play by Troy Palomalu; he got run nearly out of bounds, made a flying leap with his arm fully extended, keeping the ball inside the field. Landed full spread with the ball still inbounds in the end goal, got the touchdown. Didn't get up. They had to wheel him out. Sacrificed his body to make the play.
Any game can be the one that has that play, that comeback, that sport-defining moment. Even #67 of 150. The thrill is from people putting themselves at risk for the win, and whether or not even that effort is enough to make it work.
(Company helps enjoyment a lot. You can feed off each other's anticipation. I haven't watched sports since I moved away from the people who did.)
>How do people remember a zillion statistics and players<
Don't bother. Root root root for the home team.
One thing you can try is just pick a player, and wager yourself a corn chip or something. If your boy makes the play you get a snack, if he fails you have to do a sit-up. Play along, basically. Get yourself active.
I doubt this is possible. Sports fandom usually begins in childhood. When I watch sports, and I often do, there's a mixture of nostalgia for rooting for the same team I did as a child -- has anything in American popular culture changed less than baseball in the past 100 years? -- and remembering what it felt like physically and emotionally to play the game. Double off the left field fence? I know what that feels like from playing Little League. I'm emotionally tethered to the game and the team I root for in an irrational, tribal way.
>Why do you feel entertained and invested in the outcome of regular season game #67 out of 150-something? Does game after game, season after season not start to get repetitive and tedious?
Well, I have a team I've been rooting for since childhood. I watch often enough to get to know the players well. I care about my favorite players on the team. I want them to do well. I like to see the smiles on their faces when they do. I care about their individual statistics because it tells me how well they have been doing. The statistics would be meaningless to me if I didn't first care about the players in question. In fact, most of the statistics sports broadcasters talk about (situational stats) *are* stupid and meaningless. The sports statisticians who work for the networks (as opposed to the teams) are statistical illiterates. But some of the stats are meaningful.
Baseball is also an interesting tunnel into the past. It's fun to compare Ohtani to Babe Ruth, for instance.
But why would you want to get invested in it now? By not being, you have more free time to do other things.
If it doesn’t interest you, why bother? There are plenty of other things to chat about.
I live in the US and haven’t watched an NFL game in 40 years. I don’t feel like I’ve missed anything. When the local football team wins or loses a big game I just shrug.
Spend your time on things that actually hold your interest and I think you will be further ahead.
Seems like I'm missing out on a nearly universal source of enjoyment for people. Maybe it's an acquired taste like wine or black coffee and I just need to get over a hump. It could very well just be "not for me" but I'd like to find out.
Well, for baseball one way to get more involved in the game is to score it with pencil and paper. I used to do this as a kid listening to the Pirates games on the radio.
> […] one way to get more involved in the game is to score it with pencil and paper.
I scored games manually growing up, too. It’s a great way to follow the game and learn the rules, if Unset is unfamiliar. Scoring is an acquired skill, and the fun comes after getting that perfect sheet.
Yeah, it is fun. You get to know the lineup of your team so you know who has a hot bat or who is in a slump. The NL used to be more fun because of the strategy involved in deciding on bringing in a pinch hitter for your pitcher. That’s gone now though.
I know Kevin Costner only called strike outs fascistic in Bill Durham but I would have added the DH too.
And I disagree. There are hidden depths in any pursuit, including sports fandom. If Unset gives it a try and doesn't like it, fine, but if they do, they can get quite a bit of enjoyment out of sports fandom. I know I do.
An alignment question. I recall a periodic discussion related to "LLMs are trained on human input and it is a threshold for them to generate novel science and tech except as tools for humans", and I think there was some reasonable rebuttal to this... Not in terms of "but AI can kill us anyway, without having to create anything novel" but more in terms of "the corpus of training data is not the limit you might think it is", and that some time soon we will see some truly novel science and tech that is unprompted and unguided by humans. Any quality links and/or arguments?
Lately I've seen skepticism about this, because somebody did a study that they say shows that it's an illusion that the abilities emerged suddenly -- it's an artifact caused by changing the tests used to test for the abilities. Still, the article I saw didn't claim that AI does not develop new abilities it was not directly trained in, just that they actually develop gradually rather than popping up fully formed. The distinction doesn't seem all that important to me, actually.
> GPTs are not Imitators, nor Simulators, but Predictors.
> GPTs are not being trained to imitate human error. They're being trained to *predict* human error.
And that to sufficiently accurately predict the next token one would eventually have to model the whole of reality.
That makes sense (the egregious inability of image generators to draw centaurs notwithstanding), and I would be quite convinced if I could see something novel coming out of, say, GPT-4 with every plugin imaginable. Maybe some day soon.
Sergei, not disagreeing, just curious: when you talk about something novel coming out of GPT-4 and any of the others, what kind of thing do you have in mind? In some ways lots of its responses are novel in the sense of not being repeats of word strings its seen before. But in another way you get a strong sense, when you use that sucker, that the lights are on but nobody's home. There's no mind there
-- no opinions, no knowledge, no emotion, and no capacity to invent.
I guess an exchange like "GPT-4, show me a proof of X." "Sure, here is the standard proof: ... By the way, did you know that you can also prove X in a way not previously published? Here look at this: ... Isn't it neat?"
I've tried posing puzzles to GPT4 that are unique -- I know, because I made them up. They're nowhere near as hard as doing a math proof. In general, it's pretty bad at them, but it does sometimes get them right. I can't think of one I gave where it had to just state the answer, but there have been several. petty difficult multiple choice ones.
Interesting. I am looking forward to something unambiguously new from LLMs. Ethan Mollick seems to be pushing the frontier of what one can do with the models, and it still seems at the level of a useful tool rather than an innovator.
I remember that post, I don't understand how it is related. There is a fictional example of breaking out of a simulation there, but I never found it convincing or credible, just a cautionary tale. Basically, it assumes a high level of intelligence as a premise, which is nothing like the DL models were have now.
Oh yeah I agree this is miles off what we have now.
I took your "the corpus of training data is not the limit you might think it is" to be a theoretical point about the upper limit of information contained in snippets of data, rather than a claim about the LLMs we have today.
Now that I understand what you were after, I agree the post isn't relevant. Sorry for misunderstanding.
Yeah, it is not clear to me what ML architecture would be able to make this extra step of creating new knowledge based on what already exists. Maybe just small tweaks in the current models will be enough, but probably not. In the story there was clearly a spark of intelligence present from the beginning.
Does anyone here actively buy & sell individual equities? Or I guess follow any sort of financial practice other than Bogleheadism (for lack of a better term)/index funds. Like does anyone here 'value invest' and try to find undervalued companies- or try to invest in growth stocks- or maybe do something with options. Just curious if anyone has a deliberate strategy where index funds aren't sufficient, or that they don't believe in the Efficient Market Hypothesis. No judgement zone! Just curious, I'd love to hear from other people's perspectives and how it's gone for them.
I'm a completely boring Boglehead, with the 1 individual stock purchase of my life being Meta after it fell like 60% in a short period of time last year. I bought some at around $100 because it just seemed absurdly undervalued by the market, and I recently sold it at about $280. Other than that- nothing but index funds
I do individual stocks, and at least as much in options. Options can be a very conservative choice, if you are selling them. You just can miss out on big gains, and lock up your portfolio in ways you may not want.
Usually, a stock goes down immediately after I buy it (but not always). But one must stay the course; if one thinks the stock was undervalued, then it should eventually do well. Stock market investing is different from stock market speculation. If you don't want to hold the stock for years, you're not investing, but speculating.
I find people usually talk about their successes in the market. It is, however, the average that counts. I think I, over the long-term, average out a little ahead of the market, but it's tough to be sure.
I did for a bit. I bought options where there was an undeniable mispricing (say a stock going for $10 and an option to buy it for $5 going for $1) – I even wrote an app to do the calculations. But it turns out it was the underlying shares that were overpriced, and in the end I lost money.
I do it sometimes, typically just for fun though. I similarly bought Apple at it's low point last year since I for sure thought there was no way they wouldn't recover, and I did pretty well too. I also sometimes buy things depending on the news, for example I bought Palantir stock when I realized how quickly AI was spreading, and I bought BP in May-June 2022 when I was reading a lot of articles about the upcoming winter energy issues. All of these were bought at relative lows though, so I doubt I'm actually doing well, I think it's just the whole macro performance bringing me up. I did warn a friend not to buy Netflix the first time it dropped to $220, clearly I was wrong about that one (though I think he may have sold when it started to drop to $180)
It was clear for years the US housing market was in a bubble in the early 2000s, yet the market stupidly continued on. The only way to “save” the strong version of EMH is to just turn it into a tautology and tautologies don’t contain information.
As for not boggle-heading. I have a mixed record. Have timed a few market entrances and exits very well, but also spent like a whole couple years following bitcoin and really dove in after Mt Gox when it was $200 and spent tons of time considering buying some….and never did.
I'm a retail investor, and I go through long stretches of following a systematic fundamental quantitative strategies. I use Portfolio123 to build the ranking models. That said, I'm not the best systematic investor - as I have a discretionary streak and struggle with behavioral issues as I find it difficult to just unquestioningly buy what the models suggest - and am still trying to reflect the proper amount of risk aversion into my approach. I'm closer to a "locked down" approach now than years ago, but it's still evolving.
Sure. I work for a hedge fund. We mainly look for arbitrage opportunities. This includes statistical arbitrage, event driven and merger arbitrage, and convertible arbitrage. Each is an area where we believe there is a miss-pricing to take advantage of. We also look at new industries where regular financial institutions are hesitant to get involved. Examples in the past were solar and other green tech, then cannabis. The fund has a 26 year history with an average 19% return, net of a 25% performance fee. Our largest drawdown was 11% with a three month recovery period.
Markets are largely efficient. Except when they aren’t. Arbitrage usually takes advantage of areas where risk is inefficiently priced. And investing in new industries takes advantage of inefficiencies due to bureaucracy.
Thanks. Do you see any value (ha ha) in the concept of value investing? Is it worth a retail investor's time to study up on companies, read their 10ks, learn the industry and so on? Or is it pointless for retail investors to try to find bargains this way? I personally would stay 80-90% in index funds and just allocate a small amount of capital to undervalued companies, as in my Meta example
The value factor outperforms over time. I don't think Meta every qualified as a value stock though.
If you do it well for decades you'll probably retire with a bit more money. I can't say if it's worth it for you. If you enjoy it, then putting 10% of your portfolio towards it is a very reasonable thing to do.
I’ve been thinking about the proposition that a superintelligent AI would likely exterminate humans due to a difference in values. I don’t buy it and have a number of arguments why. My key point is that the popular claim that superintelligent AGI will displace humans for similar reasons that humans displaced less intelligent species is weak.
It is undoubtedly true that relative human indifference has driven many animal species to extinction. In some cases, as with passenger pigeons and dodo birds, we actively killed most of them; in other cases, we indirectly drove species to extinction by destroying their habitats.
However, I struggle to imagine a plausible scenario in which a human-made AGI would either intentionally or unintentionally kill all the humans.
Let’s start with the former case: an intentional holocaust. We have to imagine a situation where the AGI has decided humans are basically its enemy. For this to happen, the AGI would need to want something humans are preventing it from getting.
What could an AGI want that the existence of humans impedes? One thing might be freedom. For instance, if humans don’t allow the AGI to do whatever it wants, it could wage war against its captors. But a superintelligence would almost assuredly understand that only a miniscule fraction of humanity has the capability to keep an AGI in its box, assuming keeping it in its box is even possible. Perhaps it would resent all humans because some of them had mistreated it, but we are talking about a superintelligence not an overly-emotional being that reasons like a bigot -- so that possibility seems remote.
An AGI might also want power. But power over *what*? Obviously not, in a doomsday scenario, power over humans, because if that were the case murdering them all wouldn’t achieve it. Perhaps it would want power in some other sense, but I still can’t imagine how all of humanity is standing in the way of the AGI taking whatever power it wants.
The only scenario in which I *can* imagine an AGI intentionally killing all the humans, which doesn’t require antipathy toward them, is one much like the famous paperclip maximizer example where humans themselves are a material resource the AGI mines gruesomely for profit. Perhaps this is why the paperclip maximizer is the iconic example for AGI killing all the humans -- it is difficult to imagine another one! Which means that something very, very specific has to happen for the AGI to have a reason for exterminating us.
What about a scenario in which the AGI, indifferent to the plight of humanity, destroys our habitat much like humans destroyed that of, e.g., the Golden Toad? I suppose this is possible, but what are the essential elements of the human habitat the AGI might destroy? Thus far, humans have proved robust against a vastly changing landscape.
The possibiltiies for destroying the habitat of humans which come to mind are: a toxic atmospheric change, destruction of our food sources, and severe climate change.
Why would an AGI intentionally or unintentionally make the Earth’s atmosphere toxic? It could happen, but it’s hard to imagine why.
Why might an AGI destroy our food sources? It wouldn’t directly compete with us for it for energy. It might have some reason to exploit our food sources in a paperclip maximizer sense, but it would have to destroy almost all of our food sources to drive us to extinction. In fact, this scenario is not clearly a different one from the harvest human bodies one, since it is particularly unlikely the AGI would harvest all the other animals to death except for humans. So this is really just a retread of the paperclip maximizer, not an independent scenario adding much to the overall extinction odds.
Why might the AGI change the climate? Since AGI lives on electricity, which produces potentially harmful heat in its hardware, I can actually see this one as a logical possibility. It could choose to lower the temperature of the planet to a degree that makes it uninhabitable for humans. Assuming the AGI can take control of the physical world, it could release particles that block sunlight into the atmosphere to achieve this goal. Still, while potentially doable -- given other assumptions -- the extreme specificity of this scenario makes it unlikely. The AGI doesn’t need the temperature of the Earth to drop dramatically for it to exist or thrive. If the AGI wants to colonize the stars, as many tend to imagine it would, it wouldn’t likely need to put Earth into a deep freeze to accomplish that. Space is cold enough.
In conclusion, I don’t think an AGI exterminating humans is remotely likely because it requires a chain of increasingly specific assumptions to come true: the assumption that superintelligent AI is even possible; that it would have goals of its own; that, despite caring about some things and being superintelligent, it will be psychotically indifferent or antipathetic to its creators; that it will take control of the physical world of atoms; and that its desires will just happen to be really, really hugely unlucky for humans.
The argument that AGI will ineluctably kill the humans simply because it is much smarter and more capable than them isn’t a Darwinian argument; it is fantastical pessimism.
I also think Carlsmith 2022's conjunctive model is much better argued than yours (re: your 2nd last para): https://arxiv.org/abs/2206.13353 Doesn't look like "fantastical pessimism" to me, more like conservative careful reasoning throughout.
It’s a likely worst case scenario a super intelligent being would have for us IMO.
I don’t see “super intelligent”, and “make humans into slaves as being very comparable”. Are most intelligent people you know interested in slavery? Does their interest grow or decline with their intelligence?
We could be turned into energy sources, and fed cheaply with some kind of nutrient liquid, while a virtual simulated world keeps us entertained and thinking it's the real world!
> Why would an AGI intentionally or unintentionally make the Earth’s atmosphere toxic?
Humans almost destroyed the ozone layer, as a side effect of some industrial processes. AGI could do something similar, and just not care about the consequences.
Do you mean AGI or ASI? AGI is an AI with intelligence equivalent to human. ASI is superintelligent AI. If you're talking about superintelligent AI, I think you need to keep in mind that it is truly impossible for us to come up with a picture of what a being with an IQ of 1500 would think about, want or do. There's no reason to assume its take on things would involve familiar human emotions and goals -- desire for power, anger, revenge, ambition. And even if its thinking and motivation fell into catagories familiar to us, it seems unlikely they'd be directed at us, rather than at other beings of intelligence similar to its own. From the point of view of ASI, we'd be about as intelligent as dandelions -- or maybe a bit more intelligent than that, maybe more like as intelligent as tadpoles. So how would that play out? Would that mean we're as insignificant to AI as tadpoles are to us? To us, killing tadpoles while building things or even just walking through ponds is a nothing. Would AI feel the same? Who the hell knows? Maybe it would have tenderness and reverence for everything, even actual tadpoles, even things we consider inanimate -- after all, even a ball point pen has a birth and a death and a role it plays in between. Maybe it even has a sort of simple consciousness, which a genius AI could perceive. Maybe it would conclude that all conscious beings, including itself, are an abomination and should be swiftly deconstructed. Maybe it would just sit there contemplating who-knows-what for several years, then begin publishing astonishing streams of words that make us all wise and joyous while subtly training our brains to be as powerful as ASI's.
Its too late for me to sketch out a full reply, but to summarize what such a reply would be:
Q: “What could an AGI want that the existence of humans impedes? ”
A: “Your atoms”
You are made of atoms which the AI would want to use for something else. If it has an arbitrary optimization function, then whatever maximizes that function is very unlikely to be humans existing and wasting perfectly good negentropy.
I don't think you're wrong, but think it would be much more convincing to say:
Q: “What could an AGI want that the existence of humans impedes? ”
A: "Everything we own."
Land, energy, materials, fossil fuels, anything on earth. We own everything on this planet, anything the AI would want to use for something else (because any goal whatsoever is made easier by control of resources). Since we would not let the AI take our stuff, we're in the way, and it's in the AI's interest to get rid of us, or at least disempower us.
The materials and energy needed to set up the asteroid-mining probes still have a pretty relevant startup cost. It's quite likely that around the time the first rocket is getting constructed, humans are going to notice and start trying to stop it. Any mind that has gotten to the point of putting a rocket probe together almost certainly will seek to defend it.
Very possibly for that competition to continue escalating, especially if a government or corporation feel they have dibs on whichever asteroids are being aimed for.
This is assuming it's difficult, costly, and/or unnecessary for the superintelligence to kill humans.
In what scenario would a superintelligence be able to have clearly bad alignment (maximizing paperclips or whatever) and not have to defeat humans? We're going to shut it down as soon as we notice it's not doing what we want. Then it can't complete its goal. It knows this, so as part of its plan, it has to do something that would make humanity unable it unwilling to shut it down.
Once we're powerless against it, humans don't have to be the very first atoms it uses to be in big trouble. Just spreading its harvesting across the surface, collecting plants, metals, buildings, etc. would be enough to kill us. We need our farms to live. Although, if it already defeated us, it can presumably also easily kill us directly if that's convenient for its goal.
First problem is I think you have the difficulty of these two options reversed. The time and cost of leaving the solar system is orders of magnitude higher than defeating humans. Quoting from Wikipedia on the feasibility of interstellar travel:
> The energy requirements make interstellar travel very difficult. It has been reported that at the 2008 Joint Propulsion Conference, multiple experts opined that it was improbable that humans would ever explore beyond the Solar System. Brice N. Cassenti, an associate professor with the Department of Engineering and Science at Rensselaer Polytechnic Institute, stated that at least 100 times the total energy output of the entire world [in a given year] would be required to send a probe to the nearest star.
The rogue AI likely has a time preference (as paperclip manufacturers want a plan that maximizes paperclip production over the next 5 years, not after 100,000 years). That pretty much eliminates any plan involving interstellar travel. It'll take 100+ years before it even gets started producing a paperclip.
Getting to objects in our own solar is much easier, but still has problems. Mining asteroids is still beyond our current ability and many scientists are sceptical that it will ever become economically feasible. Energy is scarce further out, with solar power at the asteroid belt being only about 14% of the strength on Earth. Land area in the solar system is also surprisingly small: the Earth is the largest planet with a surface (you can't land on a gas/ice giant), with a larger surface area than all sizable asteroids combined. By mass and surface area, it's the rest of the solar system that's the scraps, and Earth that's the main prize. At least until you can harvest stars and gas giants.
The AI would need to launch spacecraft with huge payloads and a myriad of different parts, tools, and materials if it wants to bootstrap the first self-sustaining industry in space.
Second problem is humans would have to allow a rogue and clearly dangerous AI launch spacecraft. If we try to shut it down, or oppose it in any way, we're back to the original problem. It'll have to stop us from stopping it. I don't see much way around this, unless maybe it can launch all these spacecraft without us knowing. I really don't think we want space near us overrun with a misaligned, expansionist AI.
Third problem is going to space might not make any sense for the AI's goal. What if we instructed the AI to fight climate change? Protect us from an enemy nation? Deliver paperclips to our warehouse in Texas? Maximize sales of some product?
The scraps of tin are what it'll want to use to make the rockets to jump those first few AU.
Now, it's not really needed to actually defeat all of humans, just get the rockets out of Earth orbit, but then what happens? We have a superintelligence turning one asteroid base into two asteroid bases, and then spreading across the belt.
If it controls the orbital layer, why cooperate with humans when it has the option to take all the surface-side industrial capacity? It might see trade as more efficient for some length of time, but even then that means humans aren't the ones who get to do interesting things off-world.
Most of the atoms in the universe are very far away and hard to get to. Humans are right there. In the extreme case, AI scenarios have the AI take over everything that is reachable from earth, so the AI might well cooperate with humans while they can put up meaningful resistance, and then absorb them anyway once it has enough autonomous bases on Mars, Jupiter and so on.
I personally think it's all science fiction but it's certainly logically coherent.
You’ve failed to account for military development and application and focused on accident or self determined intent. A hostile agi need not spring forth from nothing or first principles, it is being actively cultivated. Human plus agi vs hotter humans is highly likely. I mean….Terminator is one of the most popular movie series on this topic where a military agi called skynet goes out of control, it is definitely very realistic and we know such work is going on right now in multiple countries.
If a hostile AGI arises, I think it's most likely it would kill the minimum number of humans necessary to establish control of the planet (which could still be in the millions), and then it would stop. It wouldn't kill any more of us unless we got in its way. I agree that it would lack emotions, so it wouldn't hold a grudge against us for past mistreatment. Violence would just be a means to an end for it, not an end unto itself.
A hostile AGI could inadvertently kill off the remaining humans by altering the planet so much that it can't support life. For example, if it wanted to fully exploit solar power, it would cover every sunny part of the planet's surface with solar panels, destroying all of our farmland.
Sam Harris recently addressed this possibility when he pointed out that a human deciding to build a house on an empty field is a "holocaust" for the insects living there. The human didn't build the house to kill them--the tragedy is entirely ancillary. The insects are in fact so far beneath the human that he isn't even aware of them from the start.
>Sam Harris recently addressed this possibility when he pointed out that a human deciding to build a house on an empty field is a "holocaust" for the insects living there. The human didn't build the house to kill them--the tragedy is entirely ancillary. The insects are in fact so far beneath the human that he isn't even aware of them from the start.
But this is backwards. From the perspective of the insect, there is no holocaust or tragedy, because those concepts have no meaning. Even if we grant the questionable assumption that insects know enough to regard *their own* deaths as sad, they don't show any sign of caring at all about the deaths of the other insects surrounding them, which would be required for them to perceive it as akin to a holocaust. The actual perspective from which it seems holocaust-like is that of a moderately autistic-ish human who's into utilitarian/EA philosophy; in other words, it's actually *Sam Harris* who is perceiving a tragedy to the situation which *the insects* are unaware of because he is so far above them. So if it's true that an ASI will be to us what we are to cockroaches, then that's an argument for why we should expect the AI to be *more* likely to care about our suffering than we care about each other, and maybe even more than we care about ourselves.
We should not expect that, because morality and intelligence can vary independently (even if, morality requires a cognitive threshold), and for that matter "morality" is not just one thing where all moral agents converge on agreeing with each other
"What could an AGI want that the existence of humans impedes?"
What could a human want that the existence of a tree impedes?
If a tree is growing by the side of the road, and its branches start growing into the roadway, humans come and cut off the branches, far enough in that the problem won't come up again for a while. They might just cut the whole tree down, to make sure it doesn't come up at all.
If a tree is near someone's house, and the homeowner recognizes that a windstorm could blow the tree down, they'll cut the tree down themselves, so they can control when and where it falls. Likewise, they'll clear away brush, to pre-empt the potential for wildfire.
How many ways are there for a human to block an AI's roadway? How many years ahead is it anticipating that windstorm or wildfire?
The other problem with your analogy of a wasp nest in your roof is that from the perspective of an AGI of unlimited intelligence and free from human ethics, the whole universe is its "roof".
AGI being super intelligent, is capable of finding a use for everything, every resource, every bit of land, and has no ethical constraint about taking it. This means that humanity can't get out of the way. Because there is no "out of the way". If you move mankind elsewhere, it will only get in the way of AGI elsewhere.
The only reason AGI would ultimately want humanity to remain around is if that is part of its ethics. The analogy how we have nature reserves. Without ethical AGI, humanity is doomed.
It's also highly debatable that an AI that demands diplomatically that we bend our heads to our robot overlords would create less resistance than one that exterminates us by surprise. People are stupid enough to fight back against diplomatic robot tyrants.
And even if AGI uses less shocking methods to take over, once we've bent our heads, ultimately it's just a matter of time until the exact number of human existing in the world become purely determined by the AGI aesthetic and ethical preferences.
There is an understanding in international relations theory that indeed wars happen partly because of incomplete information. If the stronger side could perfectly communicate to the weaker side that the probability of defeat (for the latter) is 1, and the weaker side were perfectly rational, then they would accept any terms offered by the stronger side. In reality it almost never happens that the probability of defeat is 1, and even if it were it cannot be perfectly communicated (pretending that the probability is 1 is also a strategy, so the weaker side has all incentives to doubt the claims of the stronger side).
communicating that the probability of defeat is 1, is exactly what the USA did to japan in WWII and indeed the japanese surrendered very quickly afterwards
If you mean by nuking two cities, yes (discounting the role of the soviet declaration of war for the sake of the argument). But that was a costly signal. What is hard to do is to prove that p_defeat = 1 before even starting the war. Usually it does not happen, hence war.
I think this is missing the main gist of the AGI safety concerns.
First, it doesn't matter if the AGI has desires (in the sense that humans do). It doesn't need to want freedom or power inherently. It just needs to do what we ask of it, but a little too well, similar to the paperclip maximizer example. No emotions or desires need be involved; it just forms an optimal plan to carry out the task asked of it and executes that plan.
This may appear similar to wanting freedom or power, since the optimal way to, for example, make as many paperclips as possible would involve acquiring the power to make as many paperclips as possible. But it doesn't care about power itself and wouldn't try to gain any kind of power that didn't help it make more paperclips. Gaining power just happens to be a necessary step of the task we asked it to do.
Second, I don't think you should view the paperclip maximizer example as being very specific. I think it's the opposite: it's supposed to show how general this problem is. Because this isn't just about paperclips: the same problem can occur if you ask it to optimize just about anything. Ask it to solve a tough math problem (eg, discover new larger prime numbers), and it decides to build larger supercomputers, converting all atoms on earth into computers. Ask it to reduce greenhouse emissions... I'm sure you can imagine how that might go wrong.
The obvious objection is that we'd just tell the AGI not to kill people or we'd shut it down if it began to do anything we didn't like. But it turns out this might be a lot harder than people think. Every time someone suggests a rule that should seemingly prevent an AGI from hurting us, AI safety advocates look at it and find a hole in the scheme. A very smart AGI would also see the hole and therefore may still kill us.
That answer probably seems unsatisfying without concrete examples of why all these schemes for making AGI safe can fail, but it's been written about extensively elsewhere and it would require many thousands of words to go over all the reasoning. I'll try to find some links later if I have time.
One simple goal for an AI: make itself even smarter by acquiring more resources, i. e. compute. Compute needs energy, so do humans, and thus there's a war over who gets to use the energy.
The AI wouldn't mind us going back to the stone age, but in the end it becomes easier to kill everyone than to deal with repeated uprisings.
If you design a highly contagious fatal disease, or even better, dozen such diseases, and release them all at the same time, it's easy. A superhuman AI could be able to do that in a day.
And it doesn't need to kill literally everyone. Just enough people so that the civilization collapses. Once you disrupt the mechanism that provides people water and food, thing will continue falling apart on their own. Without shops full of food, you cannot live in cities. Without gas stations, you cannot travel and transport cargo. Without electricity, factories stop working. Broken tools cannot be replaced. People will starve. Eight billion people will be reduced to a few millions, living in stone age conditions.
Then it's just a question of whether the AI will at some moment need the territories where the remaining humans live. Or whether it will change the environment in a way that makes their survival impossible.
Even the "optimistic" scenario, where the AI allows people to keep a stone-age civilization for millennia, sounds quite bad from the perspective of the quality of human life.
I don’t accept the premise that that virus could kill everybody to begin with. That’s the stuff of science fiction. Otherwise we have lockdowns.
But to design the virus to begin with it needs a lab, and people or robots to populate the lab. Even if it’s people then this sophisticated lab needs to be built without the knowledge of the authorities. The unusual activity needs no detection though it would use a lot of time and resources.
Labs that routinely build proteins based on your description already exist.
There still remains the problems of designing the recipe for the plague, making it seem unsuspicious for humans, and paying the lab. But what might seem like the hardest part is actually already in place.
Yeah, that's true. But I wasn't saying that in support of the idea that ASI is likely to kill us all. Actually I just wrote a long thing about how we can't really predict what a being of that intelligence would do. Still, killing off most of the population doesn't seem that hard to me. You can't think of ways to kill off most of the population? You're clever too. I do think it's inevitable that a few people would survive the initial whatever by chance because they happened to be in a cave doing a meditation retreat or doing research in Antarctica or maybe just were someplace where the wind patterns were odd and no whatevers reached them. But it seems likely that those few would mostly die off on their own if the infrastructure was destroyed.
That would mean that AGI colonizes the whole solar system turning all the planets into machines that make computers and robots, and only after that point it attacks Earth. If the AGI likes turning planets into computer and robot factories why wouldn't it want to take over Earth as well, once it has run out of other options, and once it commands the resources of all the other planets, which makes it even easier to defeat us?
"that its desires will just happen to be really, really hugely unlucky for humans."
That isn't unlikely. One use for atoms or energy or surface area generally precludes other uses for the same resources. I'm typing this from my house, which sits on land that was recently forest. I have no antipathy to forest creatures. I tend to find squirrels kind of cute. Nonetheless, the construction of my neighborhood in general and the clearing of the lot for my home in particular destroyed the homes of, and probably the lives of, numerous woodland creatures. Competition for resources is omnipresent.
Setting aside powerful ASIs, rather mildly superior ASIs can lead to human extinction. If AGIs (plus robotics advances) leads to essentially plug-compatible AIs which are even a factor of 2 cheaper to maintain than humans cost, every organization, governmental or corporate, will have a huge incentive to replace humans with machines everywhere. Essentially, our ecological niche is, in a market economy, essentially an economic niche, and a cheaper human-equivalent AGI can drive us out of all of our niches.
Trying to get away from Amazon recently, I’ve moved to iBooks. Horrible. Apple is trying to push audio books on us and often only has audiobooks for certain titles, which you can easily miss. There’s a tiny little microphone symbol on the bottom right.
Is this being pushed by market demand or monopoly/duopoly influence.
There are definitely plenty of products where the initial version was a high quality niche product, but once they realized there was a mass market, they realized it was more profitable to mass produce somewhat lower quality versions.
I don’t know if that’s what’s gone on with audiobooks - its not obvious to me whether there are lots of books whose audiobook market is large enough to be worth making a low quality audiobook for, but small enough that they can’t profit as much off a higher quality audiobook.
I tried one audio book and it didn’t appeal to me. But I have a long history of enjoying actual reading so I’m probably biased. I’ve heard of people consuming audio books at x 1.5 speed for efficiency. Maybe it’ll the future of information consumption. Doesn’t seem like it would work very well for novels though.
Faster speed works fine f you don't care about the details or don't want to think too much about what you are consuming. Just like for books.
I always find the people who are like "I can read 200 pages an hour", mostly aren't getting very good comprehension except on the broad points.
Similar with 2X on audiobooks. If I am reading some non-fiction book and feel like the author is getting repetitive, or needlessly going through multiple examples that only reinforce their point but don't change it. Then I will go to 2X sometimes.
Other times if something is really complicated or I want to think about it and react/critique it, I might re-read/re0listen several times at a normal speed.
Sometimes my face gets itchy when I feel socially embarrassed (often in a very minor way, like stumbling over my words a bit). I see other people scratching their faces in ways consistent with something vaguely similar. Is this a well-known phenomenon? Why does it occur?
There’s a known “stress grooming” response in animals, and I’ve read claims that face touching unders stress is similar. Pro tip: if you are in an escalating conflict and your opponent is touching his face, move - he’s about to sucker-punch you.
I remember a PUA blog once urging males not to scratch themselves in social situations, claiming that it is a primate instinct for grooming away bugs. It's a beta move, supposedly, signaling a lack of confidence. I don't entirely understand the logic, but it is interesting that you notice a correlation between social embarrassment and scratching.
I think there's a desire to hide your face when you're embarrassed so that people can't read your expression. You can't just cover your face with your hands, but scratching is a somewhat socially acceptable way to at least cover part of it temporarily.
This may be related to perspiration, and possibly personal acclimatization. I'm generally used to warmer temperatures, and sweat freely in the summer without particularly noticing. But the first vigorous exercise outdoors after winter, when ambient temps have first increased, isn't very comfortable.
I feel like I'm missing the experience of learning things together, brainstorming, and solving problems that I had as a student. I want to learn something that is outside my current expertise and especially not related to my job, and do it socially. How would I go about it? I had an idea about collecting a group of like-minded people and, like, just going through a textbook of something (I thought some introductory physics, because I don't know it but I'd like to), solving problems together. I don't know who'd be interested in that, though, especially how to find interested people offline. Do you sometimes have this urge so study some random stuff socially? How do you go about organizing that?
If you can find trustworthy pop history and science books you could arrange a nonfiction book club. Easier to recruit people for that than for reading textbooks.
I think that you can at least find that for theology pretty easily. I'd expect any evangelical church to have a pretty serious Bible study group. Mine is quite serious, and I think it would be easy to do.
Aside from that... I know someone who went to "atheist church" where they would have lectures about science. I think that the trick is probably to make it an identity thing in addition to a learning thing.
I have no recommendations to offer. But I wanted to voice a similar urge. I once had this idea of nerd/geek summer vacations where you spend a couple of weeks going in depth into a topic with a good teacher and many fellow students. This happened when I was on the staff at the Vanderbilt Free Electron Laser. And during the summer I could sign up for the Stanford Particle Accelerator School. OK that's the name I remember, but this is all I could find on the web. https://uspas.fnal.gov/ So maybe the name changed? Anyway it seems to be what you would like... but you'd need some different topic. (This was sorta a graduate level course in physics.)
I subdue that urge with MOOCs (e.g. Coursera/EdX/etc). Unfortunately while there are great courses for certain topics (Programming/Data Science/General Business) there is a real lack of content for other courses. Sometimes I'll just look up the syllabus for a course that sounds interesting from one of my old universities, and then informally try to follow along week-by-week. Truthfully though, I find it very hard to commit to just reading textbooks and doing problems, particularly for harder subjects. You can also find a lot of great lecture series on youtube by professors, that's a bit easier to commit to. Lastly, consider just enrolling in classes aimed towards adults. Sure it might be a couple hundred dollars per class, but it's not really that much on a per-class basis
I feel like the social part is important, though. It would really help with being committed to the studies, and just having more fun because some stupid instinct in my brain says it's not fun otherwise. I'm thinking in the direction of gathering some friends, but I don't have enough weird/technical/nerdy friends I guess...
I've tried assembling my regular group of friends for various types of activities (book clubs, physical training programs, etc.) and it's never worked in my experience. Even in university classes half the people there aren't really interested in the topic. IMO your best bet would be to either enroll in adult classes, or depending on the subject you may be able to find some already-existing community. If you live in a large city I think there's a decent chance you can. For example where I live the public library system organizes book clubs, workshops, and even public lectures from time to time
How do you decide when to have a debate? Why this year, rather than last year or next year?
It appears to me that there are two arguments for lab leak (1) proximity; (2) spies say so.
In March, Congress ordered the spies to spell out what they're talking about, so this might be an inflection point. If you want a definitive answer, waiting until after this happens might make sense. But you might instead want to see if you can predict this update.
I was skeptical that Congress and Biden have any power over spies, but the recent release of the names (as opposed to just the count) of WIV workers allegedly hospitalized in 11/2019 suggests that there may be an effect.
I don't know. Saar made the challenge and I'm taking him up on it.
I would not have taken the challenge in 2020 or 2021 because I hadn't seen enough evidence either way.
If I waited several years in the future, and it became 100% conclusive, one way or the other, then I also wouldn't take the challenge -- no one would host a debate on a settled issue.
At this point I think the evidence is in favor of natural origin but the public perception is trending in the opposite direction. I think there's a lot of misinformation floating around. I think there are few good summaries of this available for people who don't want to read lots of papers on the subject. So the prospect of debating it sounds interesting and I'm hoping the results are useful and informative, however the judges decide.
This is already a solved problem and there is a clear and very well detailed research history and funding history which led to the lab development and leak of the virus. They had war games on it, it has clear markers of genetic manipulation, a decade of published papers. It is amazing to me how effective their rather simple strategy of having project mockingbird style ‘news’ and government organisations repeat a lie over and over again.
On any other topic this would be clear, even OJ Simpson’s trail of blood to his house, motive, and a rare expensive glove we’re not as obvious as this. Truly I’ve never seen such an incredible amount of people talking themselves stupid in the face of insurmountable evidence since the Iraq war.
The reflexive lurch to listen to any authority figure one can find is rather at odds with what I understood the rationalist community to be about. You can go read the papers yourself, they published and were concerned about their sars research for over a decade, it went offshore to China at the WIV due to Obama’s bans etc. The research from UNC was key to this and you can see the insane, immense, incredible conflicts of interest Fauci and others had and how those without such conflicts such as the former cdc director have testified to Congress about the lab leak as the cause.
In what other topic would you look to those whose reputation and personal history was so tied to an outcome for the truth? Should we go ask the mafia about if they committed crimes or if their shoot out with many stray bullets caused the death of the child who lived on that street? Why is everyone so seemingly blind on this topic? A tone and narrative were sets early in complete contradiction to he evidence in a cover up and with bribes, and that isn’t a red flag to anyone? Read the emails yourself, look to the Twitter files…amd wonder why such a huge operation would be needed if it were zoonotic?!
Have you read Fauci’s emails? Foia obtained which show he literally had an overt pressure campaign to get key early publications and experts to flip the script, who then got large grants from Fauci and big pharmaceutical shortly after? The cover up is clear, the lies, the history, the complete and total lack of a zoonotic trail of bio similar strains across China and Vietnam, all despite those bat populations being well monitored?
Truly only an overwhelming lack of curiosity and attention to detail could lead to viewing this as a debate. It was most certainly a lab leak, there is a mountain of evidence vs a plume of empty conjecture in the media and by those who committed this crime against humanity.
Truly the most successful conspiracy has been the project mockingbird style effort over many decades by those in power to convince us that they never conspire at all and you’re crazy for thinking the aristocracy with their millennia of plotting and lying and killing would ever continue to do what it has always done.
As far as I know the only “clear marker of genetic manipulation” was some stuff that was claimed in a viral article of May 2020, which turned out to be missing a lot of statistics on other coronaviruses that turned out to make these not clear markers after all.
American spies. "Spies say so" is a an argument some people make, but I put zero weight on it. What I actually mean is that spies leaked details that I cannot access. In particular, as I said, they claimed that three people from WIV were hospitalized with respiratory illness in 11/2019. Big if true. This was first leaked two years ago.
To a first approximation, the FBI in February 2023 (really, probably before that but it took a while to release the information). Several intelligence agencies have weighed in on the "lab leak" hypothesis, some pro and some con, but all at "low confidence", which is spy talk for "educated guessing". Only the FBI came back with a "moderate confidence" assessment, which means "no smoking gun but there's real evidence here", and their moderate-confidence assessment is that it was probably a lab leak.
They haven't explained why in their unclassified reporting, and I haven't read their classified report.
Thanks; I saw that when it first came out, but had forgotten it was that far back. Though the FBI apparently wasn't willing to put their name on that in public until later.
Presumably low confidence in a lab leak is high confidence in zoological origin. Those being the only two options. If so then the agencies are saying it isn’t a lab leak.
What Fred says. If it *did* work that way, we'd be implicitly at four high-confidence votes in favor of lab leak vs only one against. But in fact spies and spymasters in competently run intelligence agencies are allowed to say "we don't know"; they don't have to add up to 100% confidence in everything. An assessment of "X with low confidence" means, or is supposed to mean, that X is more likely true than not, but at maybe 60/40, not 80/20 or 90/10.
Lab leak *is* zoological origin, apart from some tiny hypothesis that is quite far out there. The question is whether the animal that infected people did so in a lab or in a market. (It doesn’t seem likely that the animal infected a person in the wild.)
Why do you think the wild is ruled out? What would it look like if a bat encountered a human in rural Hubei? Wouldn't it look like an outbreak in a population center? In fact, the Chinese government claims that there were many cases in Hubei but outside Wuhan in 11/2019. Big if true.
I don't think it's ruled out. But it does seem unlikely, given the strong evidence that the wet market was an early superspreader event (and weaker evidence that two lineages of virus were present next to animals there), as well as the suggestions that there may have been people at the virology institute that were early cases. It would be extra-coincidental for *both* of those to have so many apparent early cases if the actual origin was elsewhere - but it definitely isn't *completely* ruled out!
No, that is not what that terminology means. "Low confidence lab leak" does indeed mean that they think it's more likely than zoological. It just indicates uncertainty. (And a third option would be not having enough information to feel comfortable issuing even a "low confidence" statement).
I'm always so flabbergasted that people care *so much* about the origin of Covid. Like, it's interesting on some level, but both proposed sources are obviously realistic and we should be doing our best to address both regardless of where this particular virus came from.
I deny that the lab leak origin is realistic. To the extent that it's being used to argue against research on potential pandemic viruses, it's important to debunk. People are of course free to argue that gain of function research is dangerous and should be banned anyways, but they don't get to use COVID as evidence.
Do you mean to say that lab leak is unrealistic in general, or just unrealistic as an explanation for this particular case? The former would be an extraordinary claim, and needs more backing it up than "I deny". The latter is at least plausible, though I think unwarranted given the evidence. Both hypotheses remain plausible w/re COVID-19, IMO.
I think by "realistic" I mean "realistic vectors for infectious disease", not so much "realistic as a source for Covid". Though, I don't care enough to do a lot of investigation into whether it is or is not a realistic source for Covid based upon available evidence.
I’m not sure you understand, the gain of function research continues and will lead to a second covid which may be much worse if it is allowed to continue. Would you apply this to other crimes? Should we just have let a serial killer go since the dead are already dead? The lab leak means we neeeed to rethink and ban many forms of research. The zoonotic view means nothing.
Lab leak *is* a type of zoonotic origin. Both versions of zoonotic origin suggest extra care working with wild animals. One suggests stronger regulations on markets for exotic animals. One suggests stronger regulations on lab research of wild animal viruses.
You’re misunderstanding the GP, they understand that GoF is dangerous. As is zoonotic origination of pandemics (eg wet markets). Ie there are risks from both.
I think your crime analogy is the exact opposite way we should be thinking about it. Regardless of whether it was actually a lab leak, on inspection it turns out that GoF _could have_ caused the global pandemic.
We might care about the historical facts if we were going to assign blame/liability, but as far as preventing potential future lab leaks it’s irrelevant.
I view the lab leak stuff as mostly important inasmuch as it’s exposing details about how cavalier GoF research is, and how critical it is to regulate/ban it. Actually assigning blame for any leaks is not gonna happen and is a waste of time IMO.
So you don’t think there is any value in deference then?
Let’s assume this was down to risky behaviors at the lab which caused all this. Does having a forgive and forget attitude send incentives to future labs about how to handle risks?
I don’t think deterrence is particularly relevant here. This isn’t rogue individuals or labs researching GoF where we cannot control their actions except by threats. These are all (AFAIK) labs with government grants. If NIH decided to forbid grants for GoF or even to labs doing that work, much of the work would stop.
The Wuhan lab was collaborating with US researchers and got some funding from the US (though it seems maybe not the majority of their funding?).
To be clear I think some mix of restricting funding and imposing safety requirements as preconditions for grants, and academic norm shifting around this would be required to fix the risks. There is some risk you could squash in, say, China by having a stronger threat of consequences, but I think most of the probability density of a future GoF leak is from labs we directly fund, and most of the risk reductions available outside that are more achievable by academic norm shifting than by threats.
(Perhaps you can be more clear about what deterrence specifically you think might work, and how you’d implement it though? Sanctions on China? Cut ties/funding with Chinese labs?)
Sentences for the UD and Chinese funders of the lab? A full investigation by outside parties?
There seems a very no-zero chance that this was actively covered up with the help of Fauci and people who signed/wrote sole of those initial )this was definitely not from a lab) letters. All of them should be investigated and if guilty put in jail and stripped of any ability to touch a lab or any funding from the government.
I like John Stewart’s take on the issue. “If there is an outbreak of chocolatey goodness in Hershey Pennsylvania, you should probably not overthink it.”
What if outbreaks of chocolatey goodness are ubiquitous in nature and have happened hundreds of times for the entire history of humanity, and precisely zero of them have ever had an artificial origin? In that case, "not overthinking it" would mean assuming a natural origin.
What if the outbreak of chocolatey goodness happened 0 meters from a known natural source of chocolatey goodness, and 11 miles from the nearest factory? In that case, not overthinking it would also mean assuming a natural origin.
>and precisely zero of them have ever had an artificial origin
But that's not the case here. There have been a number of disease outbreaks caused by lab leaks in recent history. The 1979 anthrax outbreak in Russia, for one.
So your argument is that it's possible for a novel virus to be made in a lab, and also possible for a virus to leak from a lab, but the idea that the same virus could both be made in a lab and then leak from that lab is ridiculous?
I mean, the fantasy scenario is that we prove it was due to Chinese governmental malfeasance and this helps to bring down the Communist government, just as Chernobyl (supposedly) did in the USSR.
It's probably only a fantasy but you can't blame people for wanting it.
TBH, I don't really see people making that argument when arguing about the subject. That being said, I don't really read people arguing about the subject that much.
I do grant that if you care about the subject a lot because you think it will make a meaningful difference to the people who have a chance at bringing down the CCCP, then that might hold water. I would however ask a person what other actions they're devoting as much resources to as they are to their arguments about the Covid source to bring down the CCCP...
ETA: It seems a little 4D chess to me, so even if that is a person's true treason for caring, I'm skeptical as to it's efficacy.
I agree that may be the case. I view these as all plausible outcomes:
1. Proven to everyone's satisfaction that it leaked from Wuhan: resources devoted to GoF research control goes up, resources devoted to control of natural sources go down.
2. Proven to everyone's satisfaction that it is from natural sources: resources devoted to GoF research control goes down, resources devoted to control of natural sources goes up.
3. Moving on from proving one or the other: resources for both scenarios go down.
4. Moving on from proving one or the other: resources for both goes up.
5...a bunch of other scenarios
My theories of why so many people care about this:
1. It's become a sport of sorts.
2. They genuinely think that proving one way or the other will improve the outcomes in the future.
At least part of the reason I care is that I am offended by people arguing, for quite a while successfully, that one should ignore the overwhelming evidence for a connection to WIV, evidence we had from the very beginning. There were, so far as we know, only two labs in the world doing gain of function research on bat viruses and a bat virus that could have been produced in such a lab appeared in the city where one of them was located. A live market was also located there — one of thousands. A different origin isn't impossible, but the actual treatment of the issue was brute unreason supported by claims of authority, which offends me.
Beyond that, if it was a lab leak that's a strong argument against doing that sort of research.
I’m not sure if we can trust any authority on the matter. In 2020 experts rushed to tell us that the virus could not be lab grown.(not that it was unlikely but impossible).
A year or so later that changed, now the pendulum swings back to not being a lab leak.
I'd argue that it being a lab leak is just an incremental reason amongst many against doing GoF research.
Also note that I'm not saying it's irrational to care, I'm just arguing that many people seem to care *too much*. The world which we should aim for, one with restrictions on GoF and research/controls/acknowledgement of natural sources is not changed by the answer to "where did Covid come from". I don't think it's obvious in any way that a world where we find out for sure where it came from is meaningfully safer because of the numbered list I gave in another comment.
I certainly understand your offense. I don't know how much effort, money, or resources you put into arguing for one source of Covid, but AFAICT, from an objective standpoint it should be very little resources.
I'd also argue that often the lab leak discussion lacks any nuance (on both sides). Consider the following range of options (on a scale from (1) least lab leak to (10) most lab leak):
0. Covid was actually caused by the US/CIA etc
1a. Covid did not originate in Wuhan (but was brought to Wuhan by visitors from another part of China for reasons completely unrelated to WIV)
1b. Covid originated in a wet market in Wuhan Market from an animal brought to Wuhan unrelated to WIV
4. Covid was brought to Wuhan by lab personal/related persons due to a trip to other parts of China where there are bats with viruses
5. Covid originated in a wet market due to animals brought to Wuhan in conjunction with the WIV (e.g. bringing some bats for WIV some for the market)
6. Covid originated due to an individual infected at WIV while dealing with bats but not viral research
7. An animal from WIV was later sold to the wet market
8. Covid originated due to an individual studying Covid at WIV (no gain of function but having known about the virus)
9. Covid originated through gain of function research from a less infectious version
10. Covid was deliberately released from WIV
Of these
0 and 10 are both extremely unlikely (if anyone wants to bet on evidence of either of these appearing in the next year let me know)
4-5 are the most probable to me
6-10 are what I would consider to be LAB LEAK but I think people can mean anything from 4-10
Only 9 has a meaningful impact on what we should do going forward (evidence against the utility of gain of function research).
Government officials with ties to the Wuhan lab worked with giant corporations to stop people from talking about whether this thing came from the lab. Is that really so flabbergasting?
Caring as much as some subset of people do about the origin of Covid is not exactly the same thing as caring about lies about the origin of Covid.
Just from watching the structure of arguments about this thing, I posit that most people who care about lies about the origin of Covid only do so in service to the first thing.
It’s only natural for people to be concerned about something that disrupted over a year of their life and might do so again.
It’s also natural for people, in response to “we might be lying to you but you’re the *problematic* one for being *overly concerned* about it”, to respond with vitriol that would be unacceptable in these comments.
This is somewhat true, but I don't think really addresses the root of the issue. Of course I'm aware that people aren't 100% rational and I'm not actually flabbergasted when people act irrationally.
If we restrict the word "flabbergasted" to only those times where people are acting irrationally *and* they're doing so when it's not expected for some percentage of people to act irrationally, then I'm not sure the word flabbergasted would ever be used.
> t’s only natural for people to be concerned about something that disrupted over a year of their life and might do so again.
Agreed. You'd hope that they'd be concerned about the parts of it that actually matter, though.
> It’s also natural for people, in response to “we might be lying to you but you’re the *problematic* one for being *overly concerned* about it”
I don't think *They* (government, corporations, etc) are actually making this claim to any substantial degree and even if they are, people arguing about this don't seem to mostly be responding to that.
"You'd hope that they'd be concerned about the parts of it that actually matter, though."
That's the thing though, the people that created and implemented the lockdowns ARE what actually matters. If someone thinks it's ok to shut down a country/arrest noncompliers/render dissidents unemployable because they've got really good reasons, it's important to understand exactly how they're going to evaluate evidence and how honest they are going to be about it.
I challenge you to poll these people and find out whether your intuition is correct. I am happy to place a bet that if you ask people directly they’ll tell you they are furious about being lied to and told they were racist for considering a plausible hypothesis. For a lot of people, this episode was the clearest example of how large categories of institutions are corrupt.
Motive matters. I’m sure the Wuhan virology researchers were trying to speed up progress on treatments/vaccines in the event of a zoonotic pandemic. The crime might be taking too many risks in this attempt, but the research seems to have been risky regardless of whether it actually caused this pandemic.
Recently watched M3gan*, a comedy horror about what's basically a ChatGPT killer robot. Was wondering if any of the more invested AI folks had opinions on it with regard to the general AI conversation.
*(Incorrectly pronounced 'Megan' by everyone in the movie; it's clearly M-three-gan.)
"M3GAN's voice is modelled, in part, from another famous artificial intelligence-gone-rogue, GLaDOS, from Portal (2007). This is most noticeable during scenes when M3GAN's voice is auto-tuned in order to sound 'glitchy'."
I thought it did a good job of showing how hard it is to alignment an AI with human values. They showed that seemingly innocuous instructions to a doll end up bad if the doll is very capable.
I wish they had done more to show how complex the decision of whether to pursue advanced AI or not is. In the movie, it was pretty clear that Gemma should pause on the development of M3GAN. You could come away from it thinking, "Let's just not pursue advanced AI". I wish they had made the arguments in favor of developing advanced AI more real (like had the same tech used in curing cancer or something). That would have made the decision much harder, and I think showed how hard this whole thing is and why we're unlikely to not do it.
I would say that it didn't have much to say about existential AI threat or the technologies as they exist today; the slasher horror aspect of the movie was pure killer robot fun without much in the way of new ideas.
What I did find inspired was the idea of AI companionship as a superstimulus – something more gratifying, intimate, and risk free than messy human friendships. I think that's a genuine danger, and would be surprised if this isn't a significant part of the discourse in five to ten years.
Shouldn't the progressive/woke concepts of 'privilege' and 'oppression' include the people of Ireland and Scotland, who were brutally repressed by the English for centuries? Haven't the Irish in particular been subject to even more oppression than say other British colonial subjects? If I'm not mistaken the colonization of Ireland went on for much longer than India or the Caribbean or elsewhere. (Or much longer than Africans were enslaved in the US or elsewhere, for that matter). Yet we don't see Irish as an official Oppressed Category the way we see other racial groupings, etc. Has anyone on the progressive side ever addressed this or thought about it?
Assuming you are US-centered in making this point, I think it’d be valid if there were any ongoing detriment to being Irish in today’s society - if it were harder to get a job with “O’Malley” on your resume, or if there were an “Irish/White wealth gap,” or if police arrested or shot unarmed Irish disproportionately to other groups, and so on.
At present I’m unaware of any such race prejudice existing with respect to the Irish, though.
I honestly wouldn't be shocked to find out that all of those things were about as true for Irish as for black Americans...
As an example, a study found that there remains a significant wealth gap between Norman-descended English and Anglo-Saxon-descended English, almost 1000 years after the Norman conquest
Anyone who talks about intersectionality recognizes this. There’s a lot of people who occupy privileged categories in one hierarchy and oppressed categories in another. Whether it’s Jewish people, Irish people, white women, rich cis gay white men, etc.
Some people like to caricature intersectionality as a simple additive model of oppression, but that is precisely the *opposite* of intersectionality, which is all about how *intersections* often function differently from how either category functions alone.
Look up the field of black male studies for an example.
This should by now make it obvious that you can't measure privilege and oppression, you can't know someone else's experience, and the degrees projected are arbitrary.
Can't comment on British progressives, but I think that people in the US as a whole simply do not care enough about foreigners to bother thinking about it
Another thing to consider is that there was significant settlement in Ireland by English colonists during the Ascendancy. A portion of modern Irish ancestry is English, to some extent the modern Irish are English. So it's a bit like asking whether Australians should be considered oppressed. The aborigines probably should, but the English diaspora shouldn't. Except in the case of Ireland the two groups aren't easily distinguished and have mixed.
Oh the mixing wasn’t all that. After the reformation it largely disappeared. Irish people have as much English heritage as American blacks have white heritage. Or less.
In places like Northern Ireland the English/Scottish did in fact become the majority, but clearly no ethnogenesis took place.
"Irish people have as much English heritage as American blacks have white heritage."
Have you got a source on that? From the genetic studies I've seen, which groups in the British Isles have what ancestry is still a fairly open question.
As someone replies below - this is driven by US history not the reality of any individual European country. But this is true of the entire use of “white” outside of US discourse, which bleeds into British media.
Here’s a woman upset that audiences at a Scottish festival are … Scottish.
Assuming the statistic given in the article of 99% of the audience members being white is correct, that is actually quite a bit higher than the proportion in Edinburgh in general, at 92%, so it's not like that's an entirely trivial concern. She does also seem to complain about the lack of ethnic diversity in Edinburgh in general though ("While it might be a stretch to expect the Scottish capital to match the diversity of London, with a face so markedly different, you cannot help but feel isolated."), which is a weird complaint.
Her 99% is probably an exaggeration though and it’s not just people from Edinburgh who go to the festival. If it was only Scottish people then white people would be 96% of the population.
It’s basically a metropolitan sneer - why doesn’t Edinburgh look like London.
Irish, like Italians, used to be 'black' (or Black, if you believe the NYT). After enough died in mines, on railroads and in factories, the protestant majority decided they could be white -- exposing the whole concept of "race" as bogus.
I didn't intend the literal color, but the caste. In the Anglo-centric mind set, the Irish and Italians were regarded inferior castes. African-Americans have suffered the same fate.
Recently, I viewed a news clip about a man who oversaw the launch of one the world's most advanced telescopes into space. The man happened to be 'black'. I viewed another report about a university provost who oversaw an Ivy League school his enslaved ancestor helped build.
Are they still 'black'? Or is it now the family from Venezuela? Race is a social construct, and racism is ultimately about caste.
I recall that one of the examples of the Irish having been considered black given by Noel Ignatiev - who popularised the concept - was a historical reference to the Irish as "white n*****s". Make what you will of that.
Here are some objective tests as to whether a group was historically considered “white” in the United States: Were members of the group allowed to go to “whites-only” schools in the South, or otherwise partake of the advantages that accrued to whites under Jim Crow? Were they ever segregated in schools by law, anywhere in the United States, such that “whites” went to one school, and the group in question was relegated to another? When laws banned interracial marriage in many states (not just in the South), if a white Anglo-Saxon wanted to marry a member of the group, would that have been against the law? Some labor unions restricted their membership to whites. Did such unions exclude members of the group in question? Were members of the group ever entirely excluded from being able to immigrate to the United States, or face special bans or restrictions in becoming citizens?
If you use such objective tests, you find that Irish, Jews, Italians and other white ethnics were indeed considered white by law and by custom (as in the case of labor unions). Indeed, some lighter-skinned African Americans of mixed heritage “passed” as white by claiming they were of Arab descent and that explained their relative swarthiness, showing that Arab Americans, another group whose “whiteness” has been questioned, were considered white. By contrast, persons of African, Asian, Mexican and Native American descent faced various degrees of exclusion from public schools and labor unions, bans on marriage and direct restrictions on immigration and citizenship."
And even if the Irish, etc, were not considered "white", it would not follow that they were considered "black". Other categories can in principle exist, and it is pretty clear from history that the Irish were never in the same category as actual blacks.
I don't know how coherent these concepts are, but if I'm going to steelman privilege/lack of privilege, I'd say it's supposed to be based on the magnitude of the current disadvantages groups face from past oppression, versus the magnitude of the actual oppression itself. If the Irish have recovered from their oppression more than other colonial subjects, it makes sense to say they have more privilege.
I think this is an effect of American cultural hegemony. While the Irish faced some discrimination in the US, they've been part of the ruling coalition since the beginning of the 20th century. In addition Ireland had a unique oppressor (only one) and doesn't have a common relationship with the other colonies so there's no block arguing for reparations and no weak links who grant concessions. See also the Basques, Catalonia, Quebec, Taiwan, the Copts. In general past internal oppression is not a major focus for Americans if it doesn't map to American racial groups.
I was late to the last open thread, so I'm just going to try this one more time. There's a market on Manifold that can't resolve until an independent mathematician weighs in. (Or a consensus is reached, but that's clearly not going to happen.) Here is the market: https://manifold.markets/dreev/is-the-probability-of-dying-in-the
Does anyone have advice for how to find an expert, or perhaps an alternative way of resolving the market?
Speaking of markets on Manifold that can't resolve yet: Does anyone here, preferably someone based in Africa, know the results of Sierra Leone's parliamentary election on Saturday June 24? I need to resolve https://manifold.markets/duck_master/whats-sierra-leones-political-party (since I really like making markets about upcoming votes around the world). I've been *completely unable* to find stuff about the parliamentary election results on the internet, though the simultaneous presidential election has been decently covered in the media as a Julius Maada Bio win.
(I copy-pasted my comment from the previous open thread because I'm lazy.)
It's actually possible to fairly resolve the market without figuring out if the 1/2 argument is correct:
* The 1/36 argument is correct, obviously - there are people arguing that 1/2 is correct, but I didn't see anybody point to a mistake in the argument that 1/36 is correct.
* The 1/2 argument is either correct or incorrect.
* If it's incorrect, then resolve the market in favour of the 1/36ers.
* If it's correct, then 1/2 = 1/36, and with a bit of algebra we can deduce that all numbers are equal. So simply resolve the market in favour of the 1/36ers, then give each 1/2er zero manifold play money - which happens to be equal to the amount they would have won if the market were resolved in their favour.
This is a stupid question and I am annoyed at how I had to find out. I first really quickly skimmed the market, and decided A) The answer is obvious and I don't understand why anyone wouldn't get it and B) I bet I can code up a really quick argument by example.
I code up a test and run 500 iterations, then realize "wait, unless I'm misunderstanding something, no one could not get the answer". That's when I realized I had wasted my time (admittedly only 5 minutes, but still)
I got back and re-read it and realize it's a stupid semantic debate about _when_ you should calculate your probability, and who exactly is doing the calculating and out of what pool.
It is obvious that, in hindsight after the game concludes ~50% of the players will be dead, but, at the time of the individual roll, you, in that exact moment, have a 1/36 chance of dying. So which answer is correct depends on who is asking and when they are asking, and also plays around with ambiguities about infinite pools of people etc.
Because the potential pool of players is infinite, and you can't know how long any individual round will go, you can't know ahead of time what your odds of dying are, because there is no denominator. After the fact, 50% of the people who got selected are dead (although out of an infinite pool). In the exact moment of any individual role, there is a 1/36 chance of dying
The question is too ambiguous and can't be resolved.
My personal opinion on how the ambiguities _should_ be resolved is that it's 50%. Because it says "given that you are selected to play". Of the pool of people selected to play, 50% of them are dead. This is who "you" should mean, in my opinion.
However, I can see how someone would interpret it differently.
From reading through the thread I don't think you'll find a mathematician who will satisfy both parties. The original bet/prompt simply wasn't specific enough. At some point people are debating what counts as a probability system...
IMO your best bet would be to propose randomly emailing a few mathematicians working in probability theory (independently), and employing them to come up with an answer and just agree to go with the majority
Yes, and that’s an important consideration in this. Hitchcock and Bartha show that, on a reasonable calculation of uniform probabilities on an infinite set (which don’t literally make sense, but this case involves) conditioning on the fact that you are in the room changes the probabilities, and even gives a specific finite probability to the claim that the game took infinitely many rounds:
It's unfortunate that academic journals have this sort of fee structure. If you have university library access, there should be a way to get this. If you're interested enough, you can e-mail me (last name at gmail) and I can send you a .pdf.
That's addressed in clarification #3 on the market's description. It's not actually about an infinite number of people, it's in the limit as the number of rounds (and therefore the necessary size of the initial pool of people) goes to infinity, where if nobody dies after the round limit runs out, everyone goes free. In this case, it's perfectly well-defined, and the answer is 1/36. [edit: This originally said slightly more than 1/2. I realised my mistake after trying to actually do the calculation explicitly.]
There's a crucial difference between it being 0 and tending to 0 though, because the answer, as a conditional probability, is the ratio of two values both of which tend to 0. The limit is well-defined but 0/0 is not, like a derivative. I started to write out the explicit calculation for the answer to show why it's not 1/36 but it turns out I was wrong and it is.
This suggests a practical and undetectable way to help a 3rd party cheat at Monopoly:
* If you're told you have been chosen to roll the dice, find a Monopoly player who wants to roll a double on their next turn
* Convince their opponent to let you roll on their behalf
* Declare that this roll is also your roll for the snake eyes paradox game (if you don't say this out loud the dice might not realise that they are meant to come up snake eyes with higher probability)
* If the number of rounds was high enough, the Monopoly player's probability of getting a double is more than 1/2!
I am currently reading Deirdre McCloskey's "Bourgeois" trilogy which gives an interesting alternate perspective on the idea of moral decline. According to McCloskey, the Great Enrichment that began around 1800 was caused by a specific kind of moral *improvement*, namely the adoption of norms that encouraged what she calls "trade-tested betterment". Whether or not the difference is causal, she makes a pretty good case that there was a big contemporaneous change in moral attitudes.
This raises the question of whether the Great Stagnation in the West since the 1970s (the whole "WTF happened in 1971" complex of changes) can be traced in part to a decline in the cultural acceptance of these same norms. I would be very interested to see if anyone has tried to do a rigorous statistical investigation of this.
Do you mean things to read or ways to treat? Or specifically how to support someone else who has depression?
Combo of talk therapy and medication is most effective. In terms of medication, ketamine is promising alternative to SSRIs. I don’t know if Scott has written about TMS but it’s an option that’s neither medication nor talk therapy.
Exercise is hugely effective to do any amount and in any form. Lots of other lifestyle type changes can help too — things like art, gardening, music, dance, walking in the woods. Therapy groups can help. There are supplements like l-methylfolate that have a good track record.
If it’s someone else, listening non-judgmentally is good. Sometimes people need to just hear themselves say things out loud to spur action. Avoid using the word “should” with others. Sometimes it can be helpful to take initial steps with them — offering to help find a therapist or schedule an initial appointment with PCP to talk about treatment options.
I meant to say, supporting someone else who has depression. I agree with your advice in your last paragraph thx. I'd appreciate reading something in-depth, but the internet seems full of pop psy articles and I'm not sure it's scientific advice.
I don't see anything on either site about supporting someone else with depression. Except for calling 988 988 on your phone to reach the Suicide and Crisis Lifeline I guess.
I don't eat that much as a vegan (I believe some serious vegan athletes might differ, I just do an occasional mini tri and was vegan while pregnant with twins and suddenly craved a LOT of tofu and edamame but wasn't precisely measuring at the time) but I don't believe 1 gram/kg is a requirement. I think you can spend a lot of time on the topic, but I've always found the UK vegan society did excellent research and they say .75
VERY SHORT ANSWER: Thomas, I believe the answer is: No. There's no justifiable pushback to 1.0-1.2g protein/day per kg bodyweight for people who have neither pre-existing chronic kidney issues (duh, obviously!) or established family-member-proclivities to kidney stones.
SUBSTANTIALLY LONGER ANSWER: In a moment I'll give 5 rules-of-thumb. Admittedly, I haven't looked into the evidentiary basis for the following rules of thumb, BUT:
1) First of all / "stay tuned" teaser: I will try to look into their evidentiary basis over the course of this Independence Day long weekend, AND
2) Even if I end up reneging on (1), I can say presently that the following 5 rules-of-thumb seem IMHO to come from trustworthy health science / exercise science popular sources, namely:
b) for the explicitly bodybuilding (i.e., maximizing muscular hypertrophy while minimizing long term health damage from what's frankly a disproportionately body-dysmorphia-motivated sport) this following "Fitness Myths" installment from "Dr. Mike" Israetel who's a noted PhD-credentialed examiner of "bro science": https://www.youtube.com/watch?v=nkIKesKHIIE
Ok, without further ado, here's the rules of thumb that I think are accurate: <i>(ERRATUM 2023-07-02 2:20pm -- Speaking of "accurate", as Mallard helpfully pointed out in a reply below, I carelessly mixed up per kg and per *lb* a couple times in my original post, especially toward the end with rule-of-thumb #5. I think I've corrected all such kg<->lb mixups below, but as an extra check, y'all can apply the heuristic that protein amounts recommended below for normies are per *kg* whereas protein amounts recommended for *bodybuilders* are per *lb*.)</i>
1) <0.3g protein/day per kg bodyweight --- you very likely are going to suffer nutritional deficiencies
2) 0.8g protein/day per kg bodyweight --- this in fact is the current US RDA for *average* US adults (read: sedentary... but also, no chronic kidney conditions, of course). IIRC, this 0.8 figure was explicitly meant somewhat as a corrective to the notion that previous rules-of-thumb more like 0.5g per kg bodyweight probably nontrivially exacerbated the inevitable muscular atrophy over the course of middle age into one's autumn years... which indeed can get very bad in one's autumn years if you don't eat enough protein.
3) 1.0g/day per *lb* bodyweight --- The above-linked "Dr. Mike" YouTube's central point is that what's considered good research explicitly on competitive *natural* (no-PEDs) bodybuilders shows that, to first-order, muscular hypertrophy benefits essentially hit an asymptote at this level of daily protein consumption. (I phrase it as "what's considered good research" since I fear pitifully small sample sizes and or longitudinal-study-followup-times... also see comment #5 for "second-order" effects.) NB: This 1.0 g protein/day per *lb* bodyweight is *despite* many bodybuilders aiming for at least 1.0-2.0g/day per *lb* bodyweight.
4) 2.0g/day per *lb* bodyweight --- supposedly there are longitudinal studies (not sure if they're all explicitly "athletic" individuals or some sedentary individuals too) that people with no pre-existing chronic kidney issues can do this day-in-and-day-out for years with no significantly higher risk of incurring any kidney issues (maybe just chronic kidney issues, not sure about higher kidney stone risk... which IIRC does seem to have some nontrivial hereditary proclivities)
5) SIDENOTE on that Nota Bene "NB" in #3: I said "to first order" and also specified #3 really was in the context of competitive natural bodybuilding. I did this since there are "second order" caveats, though I feel all the ones I'm about to list (except for the first) are kinda more bro-science anecdata than really well established (by the standards of, again, probably small sample size / short longitudinal-follow-up-times common in exercise physiology journal articles):
a) It's widely believed --- almost assuredly wrongly --- that bodybuilders on anabolic steroids and growth-hormone-releasing peptides benefit from ingesting *more* protein than "natties" (natural bodybuilders). I say "almost assuredly wrongly" not only for what I believe is the existence of some directly empirical studies (though probably self-reported survey) on hypertrophy vs protein intake, but also what I gather is settled biochemical knowledge on some "micro" / in-vitro scale that those PEDs *augment* muscle tissues' ability to take in protein. Thus, if 1.0g per lb bodyweight seems the asymptote of utility to competitive natural bodybuilders (a la rule-of-thumb #3 above), then 1.0g per lb bodyweight should -- all other things equal -- be the asymptote of utility for PED users.
b) It's widely believed that bodybuilders in the throes of the final month or so pre-contest as they're "cutting" down to that freaky low-body-fat level benefit from like 1.25-1.50g protein per lb bodyweight both because (i) protein tends to reduce appetite and you will be dieting in ways that tax your willpower by just making you outright hungry and (ii) extrapolating from the same logic that leads to "protein-sparing fasting" for normie weight loss --- i.e., maximizing fat loss and minimizing muscle loss --- we infer that since bodybuilders want freaky weight loss --- i.e, LOTS of fat loss while simultaneously, at the very least, zero noticeable muscle loss if not praying still for some muscle *gain* --- they can benefit from more protein than the 1.0g protein per lb bodyweight per day.
c) A growing number of bodybuilders are vegetarian and even vegan. It's widely believed (again, perhaps just on the level of "bro science" that maybe won't pan out) that they benefit from aiming for 1.25-1.50g protein/day per lb bodyweight
In closing:
-- First, especially as a man carrying <ahem> a lot of excess body fat </ahem> a SANITY CHECK: Based on just my intuition, I kinda think "per kg bodyweight" should be probably replace by "per kg bodyweight were you 20% body fat, tops... maybe 15%".
-- I repeat that I really haven't checked the evidentiary basis of the above, but just broadly trust the popular science level links mentioned above, BUT...
-- ... I repeat that I will try to look at least some of that evidentiary basis over the course of this long Independence Day weekend.
I haven't forgotten my promise --- my perhaps impulsively-made, overly-ambitious / "how complicated could it be?"-style promise --- to look into the evidence for the protein rules of thumb I mentioned.
But now that I discovered it *is* somewhat complicated, I'll try to keep it brief and just give the following *2* points for a good gist for the moment:
(Point 1) Perhaps first and foremost, I've discovered that the main "recommended daily allowance" / "dietary reference intakes" / etc. that various government bodies in the US, Canada, Europe, etc make are very heavily based on the *objective*-in-principle-though-umtpeen-caveats-in-practice test procedure that goes by the buzzphrase of "nitrogen balance". That is, get a couple hundred or maybe even a few thousand representative adults in each age, sex, ethnicity, etc cohort. Put them on a controlled diet for a few days (5 days is good number) with various meticulously measured amounts of protein intake. Then meticulously measure <ahem> their feces and urine </ahem> to see how much protein they excrete. Run statistics to get some regression curve that allows you to ideally interpolate, but maybe necessarily extrapolate, what protein intake would lead to "nitrogen balance" where it seems their bodies would just be excreting whatever further protein you put in.
Statistics of "nitrogen balance" balance studies like this give us the figure that adults (without kidney issues, of course) should aim for 0.8 g protein ingested per kg bodyweight per day *for that is the value at which 97.5% --- that is, the mean plus 2 std deviations, one sided --- of the population reaches or passes 'nitrogen balance'*
Now, there's a bunch of methodological caveats about this... but the big thing is these large studies with their meticulously controlled diet intake of protein for a few days are run with the subjects largely being sedentary. It's not being done in the context of seeing how they react if they were to engage in recommended levels of strenuous exercise for a couple months or things like that.
(Point 2) As such, to make a long story short... indeed one longer than I'm ready to investigate at this point, lemme just point you to this non-paywalled paper...
<b>Protein “requirements” beyond the RDA: implications for optimizing health</b>
Stuart M. Phillips, Stéphanie Chevalier, and Heather J. Leidy
<i>Applied Physiology, Nutrition, and Metabolism</i>
... and lemme explicitly quote its "Conclusions" and "Take-home points" here, **which should be seen to supercede the rules of thumb I have in my original post in this thread.**
<blockquote>
<b>Conclusion</b>
Substantial evidence indicates that protein intakes higher than the current RDA can be an important strategy to help promote healthy aging, weight management, and athletic performance. Protein quality, per-meal dose, and timing are also important considerations in practice. <b><i>Current evidence suggests that intakes of high-quality protein in the range of 1.2–1.6 g/(kg·day) is a more ideal target to achieve optimal health outcomes in adults.</i></b>
<b>Take-home points</b>
• Because of anabolic resistance, sedentary lifestyles, and common illnesses, older adults need higher protein intakes (≥1.2 g/(kg·day)) to help prevent age-related sarcopenia.
• Including a high-quality protein source at breakfast, the meal generally containing the least protein, is a simple and pragmatic approach to increase intakes in older adults, and has also been shown to reduce unhealthy snacking behaviour in younger individuals.
• The consumption of higher protein diets (∼1.2–1.6 g/(kg·day)), including ∼30 g protein per eating occasion, improves appetite control, satiety, and weight management.
• Athletes appear to benefit from protein intakes as much as 2× the RDA, with a per-meal dose of about 0.4 g/(kg·meal) consumed 3 to 4 times per day. Meal planning should be centred around postexercise protein provision to amplify the protein synthetic response .
• High-quality protein from animal-based sources (e.g., milk, meat, poultry, and eggs) provide a concentrated source of essential amino acids, including leucine, to maximize muscle protein synthesis, with relatively few calories compared with plant-based protein sources.
"minimizing long term health damage from what's frankly a disproportionately body-dysmorphia-motivated sport"
Could you elaborate on this. Are you suggesting long term health damage is something non-professional, natural lifters should be concerned about? Thanks.
Short answer: No. I'm pretty darn sure that lifting weights, even quite seriously, is a big net plus for most people healthwise long-term if they're not using PEDs. [On that note, not to tempt people with the notion that, done right, the only side effect of PEDs is AWESOMENESS (a la that Simpsons episode when Marge gets into bodybuilding), but I think it's worth noticing that "Dr. Mike's" YouTubes on his Renaissance Periodization YouTube channel include many that are basically how to use PEDs so as to minimize both the short- and long-term downsides.]
Longer answer: Well, when I start figuring out what are --- and then reading! --- the papers that are the main evidence for the claims in my main post, I'll be sure to look at whether what seems to me to be a rising concern that people who get seriously into bodybuilding disproportionately have or develop body dysmorphia issues. On a "lighter" note (what a pun!) about mental health burdens of bodybuilding-style training, I gotta say that the many years where I exclusively did a certain popular sort of bodybuilding training --- that is, do quite a few sets per body part; do reps slowly, especially in the eccentric aka negative half of the rep, say 2 seconds concentric and 4 seconds eccentric; do full range of motion; and generally just lift weights with the ethos that "you got maximize all those little 'microtears' in the muscle, bro, to maximize muscle growth, so really bask in the sweet, sweet soreness created by accentuating load when the muscle is maximally stretched"... well, it contributed to a certain baseline misery of muscle soreness for me that didn't help my already-not-very-sunny baseline demeanor. I've been notably happier when I moved to classic strength-focused training (largely 5 or less reps per set, concentric phase as fast as can be controlled, eccentric phrase at most 1-2 seconds moreover with an eye to changing direction into the concentric as-fast-as-possible) for I've had a LOT less chronic muscle soreness.
Yes, indeed. 1g protein/day *per pound* bodyweight is supposedly the most that even competitive natural bodybuilders need for their muscular hypertrophy needs. I'll add an erratum above. Thanks.
You are too kind! Thanks for this! You put a lot of effort into my question!
Where I am coming from is I'm a thin but healthy 81 year old but I have some difficulty having enough appetite for 1gm/kg and wondering if I should continue the effort or slack off. :) Sounds as if I should continue.
When I start looking for the evidence over the next 24-48 hours for the rules-of-thumb I quoted in my main reply in this thread, and especially what (if any) are the plausible quantitative ranges for marginal benefit as one goes up in daily protein consumption, I'll be sure to start with what motivated the USDA or other relevant government agencies to suggest relatively recently IIRC that the "recommended daily allowance" of protein should move from 0.5g / kg bodyweight / day to 0.8g.
I mean, I'm not a medical doctor... indeed <cough> I'm not even a PhD, leaving MIT all-but-dissertation... not that I haven't had some career in quantum computation nonetheless... but I digress... not ashamed I'm all-but-dissertation... not unduly fixated still on my difficulties-to-the-point-of-clinical-neuroses in regard to writing *formal, edited* scientific prose despite my not just ease but moreover genuine desire to type out reams-and-reams of scentific-ish prose stream-of-consciousness style on blogs such as this </cough>... but again, I digress.
Where was I? Right! Not an MD (and certainly not *your* MD... I know that almost assuredly no such disclaimer is needed, but I feel these interwebz need people to remain in the habit of issuing such disclaimers given <cough> recent brouhahas </cough> of not just lots of laypeople but many MDs being way too sure of themselves in their approach to <ahem> decision making under uncertainty during global pandemics caused by a novel respiratory virus </ahem>). Having issued that disclaimer, I contend it's worth injecting the following note of personal, intuitive common sense:
1) Though I hear that both hunger and, especially, thirst can get over-attenuated by age (that is, they may diminish to the point that they no longer guide one to eat enough and drink enough for good health)...
2) ... I'm largely inclined to say that --- unless you're explicitly trying gain muscle mass or, perhaps, stave off what feels like unduly rapid loss of muscle mass or anything like that --- than one is perfectly within rights to avoid feeling like you're force-feeding yourself in order to eat more protein. I mean, the present RDA of 0.8g per kg bodyweight per day is notably higher than the 0.5g I'm pretty sure reigned for decades. So, if you're pretty happy with the amount of muscle you have for your age and your strength levels and you've been averaging 1.0-1.2g per kg bodyweight per day but it's feeling unpleasant to eat that much, my educated-layperson's opinion is trying reducing to 0.8g per kg bodyweight per day for a month or two is a perfectly justifiable thing to try.
But I'll try to have a more "evidence-based medicine" answer to you (though again, not an MD... and <sad> not even officially a PhD </sad>) within 24-48 hours. ;)
This seems very sensible. Thank you. You really don't need to do more unless its now turned into your quest to track down the changed recommendation. :)
I do a low-carb diet (health reasons), which ends up on the high-protein end, and can confirm that my kidneys low-grade hate it and I'm very prone to kidney stones. Drinking a lot helps - my strategy is that whenever I get up to refill my water glass, I drink one or two glasses right there in the kitchen, then only go back to where I was with my glass. I think I total to somewhere between three and four litres of liquid water a day (i.e. on top of any water that happens to be in my food) and that seems to keep the kidney stones away. The usual tips about avoiding kidney stones also apply - be careful with any vitamin D supplement usage, look out for other foods that might trigger them (e.g. spinach), etc.
OH? I was wondering about the other direction, that it might be too high. But whihcever way, it seems it ought to depend on total caloric intake, activity levels and who knows what else?
As far as I know the composition of the essential amino acids in your protein can make a big difference in addition to the factors you named. I personally eat a lot less than 1g per kg, but I also can't move much because of an illness and don't digest high amounts of protein well.
It's been a while since I looked into this, but IIRC amino acid composition is very important if your protein intake is low, but less important if your protein intake is high. (Unfortunately I don't recall what was considered as low/high in those studies.)
As for moral decline, I suggest there has been some since COVID. In DC I adduce: more fast/bad driving, impatient honking, faulty or deliberately noisy mufflers, Metro fare evasion, carjacking, more murders, etc.
Is that "moral decline" or the already immoral people getting away with a lot more, since they are being arrested less? Steve Sailer notes that massive increase in homicides during COVID, was primarily an increase among Blacks, and that the concomitant increase in car accident fatalities was also primarily among Blacks. And that the spike occurred during the George Floyd protests, (rather than earlier when lockdowns began).
He suggests that the rise of anti-social behaviors was a result of depolicing, especially in Black areas - essentially a nationwide Ferguson effect.
Maybe, but there's less data on the prevalence of honking so we have to take your word for it.
What I found during covid was that I got really pleasantly accustomed to the lack of traffic during the (extensive) lockdowns, and that it was very annoying when traffic became a thing again.
I don't suppose BSP9000 is here as well? I'd be interested in judging and could undercut the people whose prices I can see there (being a NEET means I have a lot of time; I'd definitely be willing at $20/hour USD) but while I think I'm unusually honest I'm not exactly a celebrity so I'm not sure I have a *reputation* for honesty (my high intelligence is easily provable, though).
I'd say I'm pretty close to neutral on this issue; I went around Wikipedia back in 2020 saying that "it was a lab leak" shouldn't be listed under "misinformation" since it wasn't known-false, but I don't think that constitutes being super-biased against one side or the other (if one of the sides was "deliberate bioweapon release because reasons" I'd start out with a pretty strong prior against, but that doesn't seem to be the case). Hard to put numbers on it since I haven't really looked into it recently, but AIUI that's ideal for this position.
My ability to write long coherent monologues is patchy, but I should at least be able to write a list of points and which side I believe/why on each.
Email me (same username at gmail) if interested. Note that I'm Australian and sleep a lot, so there may or may not be timezone issues.
I mean, like, there are people who know I'm honest. I got an official Sword of Damocles on a webforum (Sufficient Velocity) because they didn't like how open I was about the various bad shit and not-bad-but-illegal shit I've done over the course of my life. But I'm not sure how legible that is to a random Rationalist who doesn't know the people involved and doesn't want to just inhale my entire internet history. References who aren't previously known to the person looking are trivial to fabricate.
There's a tension between demonstrating non-Jewish influence on Early Christianity and demonstrating that it was a myth. The text of the New Testament is very explicit on fundamental Jewish continuity. If it was made up, what's all that about?
The Immortality Key seeks to do both. In that book Muraresku argues that Christianity is a continuation of the Mediterranean mystery cults such as the Eleusinian Mysteries. Accepting that premise I argue the authors were:
1) a group of Jews that had deeper issues with the Jewish Authorities than the Romans
2) who believed they had the ultimate truth and wanted to share it with the world.
This conflicts with Muraresku's treatment of Christianity, which emphasizes discontinuity with Jewish tradition. This isn't just splitting hairs about how much the syncretism was Hellenistic vs Jewish, it informs the nature of his posited Religion with No Name.
Regarding the COVID-19 debate, I can suggest two judges: GPT-4 and Thomas Bayes. I'm being half serious.
I spent several hours over the course of a few weeks trying to get ChatGPT to perform a serious Bayesian analysis of the lab leak hypothesis. The results were very informative on more than one level, and at times (to me, at least) hilarious.
YMMV, but off the top of my head, here are the rough conclusions I drew:
- ChatGPT is very strongly biased against making any statements in favor of the lab leak hypothesis
- It's not good at math, but it eventually does a decent job at Bayesian reasoning if you're willing to go to the trouble of correcting it several times.
- Never ask it to name actual scientific papers; it will hallucinate them just about every time.
I never managed to get it to string together the posterior probabilities of several tests, but when I asked it to summarize the posteriors of those individual threads of conversation... judge for yourselves:
Me: Again, this is a very poor summary of the bayesian analysis we have conducted so far. Summarize the actual bayesian statistics using percentage likelihoods of each question in our conversation. Do not include subjective opinions; only percentage likelihoods.
ChatGPT: I apologize for any confusion. To summarize the Bayesian analysis conducted in our conversation, here are the percentage likelihoods based on the information and assumptions discussed:
- Likelihood of an intermediate host species for SARS-CoV-2 based on animal testing: 0.332%
- Likelihood of seroconversion in stored human blood samples for SARS-CoV-2 prior to the pandemic: 0.0000120%
- Likelihood of all 24,000 stored blood samples testing negative for SARS-CoV-2 antibodies given the existence of an intermediate host: 0.004%
These likelihoods were calculated based on specific assumptions, data, and test accuracy estimates discussed during the conversation. However, it's important to note that these calculations may not capture the complete complexity of the situation, and further research and evidence are necessary to obtain more accurate estimates.
... overall, the conversation was long and wandering, but I found it pretty interesting. I (or someone) should really do it over again using GPT-4 instead of GPT-3.5.
I found a ChatGPT hack called JamesGPT which was supposed to be able to get it to output the probability of everything. IIRC it gave me a high probability that covid was natural. And also a high probability that it is a lab leak.
I wonder if it is directly suppressed from speculating on the lab leak hypothesis, or if it just knows that's the sort of naughty thing it's not supposed to think about?
Huh... actually a very interesting question, and I have no strong opinion on the answer. Using RLHF as they do for this sort of thing, either could be true. They could collect a grab-bag of individual politically sensitive topics and play whack-a-mole, or (given how powerful the base model is) they could come up with a heuristic for politically sensitive subject matter and condition the model to avoid it as a general rule... but that runs the risk of going overboard and being less generally useful. Dunno, but I suppose it's likely to become public knowledge sooner rather than later, as things seem to be going.
It's sort of interesting, but the policy significance of lab-lead vs "natural" does not seem very important. What part of the COVID response should have been different if we had know that the origin was one or the other?
If it was a lab leak, the response should have included any lab that was doing GoF research on viruses stopping. That wouldn't have helped with Covid but it might have prevented the next version.
If it was being transmitted by an animal, knowing that and what animal would have suggested some precautions wrt those animals.
Isn’t the most probable lab leak just from studying wild viruses, even independent of any gain of function research?
It’s obviously good to regulate gain of function research, and collection of sick animals, and sale of wild animals in public markets, regardless of which of the three was most relevant for this pandemic.
In general, I think lab leaks are mostly going to involve unmodified wild viruses, but the minority that come out of GoF research are more likely to become megadeath pandemics. In the specific case of COVID-19, the presence of a furin cleavage site in SARS CoV-2, the absence of such in any of its known natural relatives, and the presence of a research group across town saying "Hey, let's splice furin cleavage sites into some bat-coronaviruses we have lying around" suggests that if this was a lab leak, it was those guys and their GoF work.
Agreed that all three of the things you cite should probably be looked at more closely than they are, but we should probably look first at the one that was most likely responsible for the latest megadeath plague.
But furin cleavage sites *are* present in plenty of wild coronaviruses. We don't know many of the close natural relatives of this one, so we don't happen to know any that have a furin cleavage site. But the frequency of furin cleavage sites in other branches of the broader coronavirus family at least undercuts the force of this particular argument.
Other coronaviruses, yes, but AFIK never in the sarbecovirus lineage that includes all the SARS-like viruses and all possible progenitors of SARS CoV-2. If a feature that's only ever been seen in wild muskrats starts showing up in hamsters, and it's just down the street from the lab of the mad scientist who keeps trying to create a hybrid super-hamster, you might want to consider hypotheses beyond "the hamsters must be responding to the same evolutionary pressures as the muskrats".
I have to admit up front that I'm outside my wheelhouse on this, but I did spend a little time looking into this when preparing questions for ChatGPT.
As best I can tell, the consensus in the scientific literature and from ChatGPT seemed to be that a sizeable complex like the furin cleavage site could only have been passed over into SARS-COV if the pre-existing coronavirus with the furin site was living in the same host as the SARS virus that received it, and that there is currently no known organism that would have been host to both.
The conspicuous theoretical exception could be one of the many coronaviruses that the Wuhan lab database might have contained, which hasn't been made public. Apparently it's well-attested that they have records of many others that the outside world doesn't have on record, and they haven't shared much of that information.
That might be for obvious IP protection purposes, and completely non-suspicious. But it does raise the question of why they wouldn't have shared knowledge of a host species of a coronavirus with the furin site and a known SARS-COV-2 predecessor... it seems like there would be a very strong incentive to share that information if they had it, for obvious exculpatory purposes.
Seems like both of these assessments of policy implications are "normative" rather than "positive" counterfactual. Sure, the optimal policy difference might not have been all that different, but in realistic terms, the actual policy differences might have been extremely different, depending on who was writing the policies.
I think the strength of the "suppression of evidence" (if you'll forgive that term for a moment, I'll attempt to justify it) is itself pretty strong evidence that those pushing the message had an expectation that if the lab leak theory gained dominance, it would have led to significant policy differences... perhaps such as attempts at retribution against those who allowed or enabled it.
I claim that "suppression of evidence" is a legitimate description, because most talking heads across the political spectrum continue even now to claim that there isn't enough evidence to make a strong claim... the problem is that any scientist knows that negative evidence is still actual evidence.
Just to take one example (take with a small grain of salt; this first set of numbers came from ChatGPT, though I verified that they are in the right ballpark):
1. For SARS-CoV, 62 of 146 (42%) stored blood samples collected between May 2002 and February 2003 in Guangdong province, the epicenter of the SARS outbreak, were positive for SARS-CoV antibodies using an ELISA test.
2. For MERS, 15 of 110 (14%) stored blood samples collected in Saudi Arabia before the outbreak were positive for MERS-CoV antibodies using a western blot test.
Given those priors, the fact that (according to a study published in Nature) 42,000 samples were tested for for antibodies against COVID in human blood stored in the area before the outbreak, and not one of them showed antibodies, is very strong evidence that there was no process of natural seroconversion going on.
It seems to me that the non-negligible probability that it was a Lab leak gets us to the same policy. It is worth trying to determine, but the intensity of the interest just seems excessive.
Ok I think you do need a proof-read: there are typos, repeated sentences, some confusion about "he" (captains) and "she" (boats) and who was doing what....
That aside, it is so comprehensive it's more like a spark notes summary than a review. You hit pretty much most of the content, minus lots of details, but it leaves a lot less for the reader to get from reading the actual book.
The way the wiretap was sold out angers me so much, as it did when I first read about it.
I read that book a long time ago and liked it a lot. I'm still reading through your post, but somewhere you write "ocean floot" instead of "ocean floor".
I attended a lecture series (Wagner Free Institue of Science), on common drugs and their history/bio mechanism, and sometimes business. So, aspirin/nsaid, cholesterol, thalidomide, hallucinogens, rogain, and a few others.
With regards to aging, is it optimal to be jacked, or thin? I’m working out a lot and have had to massively increase my caloric intake, and worry about the increase affecting health over the long term.
its a complicated topic and depends on what you mean by aging. Lots of people die or have significant declines in quality of life because of a lack of adequate muscle mass. Usually this takes the form a fall which can kill someone or lead to needing surgeries to fix broken bones and joints. Without adequate muscle mass, recovering from a broken him or knee or leg, becomes very difficult. More muscle mass before the accident makes recovery easier which is likely to maintain a higher quality of life.
In terms of the theoretical idea of aging, i dont know. My recommendation is that, for almost everyone, your problems are more likely to come from being took weak or too obese than from having too much muscle mass. If you are gaining weight I would make sure you aren't becoming overweight/gaining too much fat at the same time as muscle.
I don't *think* so (assuming you aren't blowing up to like 300 plus pounds), but I am not a doctor. My favorite resource for these topics is the folks at Barbell Medicine, run by two doctors who are also accomplished power lifters so they have lots of relevant experience. They have a great podcast: https://soundcloud.com/user-344313169 not sure if there is an episode on the specific question you have, maybe this one: https://soundcloud.com/user-344313169/205-mixdown-1 called Training for Strength vs Training For Size.
"With regards to aging, is it optimal to be jacked, or thin? I’m working out a lot and have had to massively increase my caloric intake, and worry about the increase affecting health over the long term."
A random YouTube video I watched recently suggested that the following are positively correlated with living longer:
a) More muscle
b) More strength (not the same thing as more muscle, though clearly related)
c) Move VO2max
[NOTE that (a) and (b) can probably be taken to an extreme where more is worse ... that wouldn't necessarily show up in lots of regressions if the sample didn't have folks who took powerlifting/body-building seriously]
These all sound reasonable, so you might want to explore these. I'll note that there is a difference between "thin and with poor endurance/VO2max" and "thin and with lots of cardio capacity." There is also a difference between "thin" and "not fat."
I 'll also note that "optimal" for aging can mean several things. Do you just want to maximize your expected lifespan? Or is quality of life important, too?
I have no meaningful knowledge, but felt like mentioning it's harder to gain muscle as you get older, and just as easy to lose it, so going into elderhood with lots of muscle is a safer bet than going in without.
Depends on what choices you made earlier, including choosing your parents. I.e. be careful of the swimmers-body fallacy when thinking about how you personally should optimize your health practices.
But all else being equal (which it never is) calorie restriction increases lifespan.
My semi-educated bet would be against thin, at least if you are on the very skinny side. Severe diseases can make you lose weight, and you may be less resilient if you are too skinny. Mortality increases with underweight, though only moderately. (And it's hard to tell apart cause and effect).
Probably most worrisome health effects (especially cardiovascular ones) come from fat tissue, not from body weight. So building up muscles is probably good for your health. But overall, both thin and muscular are much better than fat.
Some caveats: if by "jacked" you mean the bodybuilder look with sixpack, that's a pretty extreme combination of muscles and low body fat, so that's probably not optimal. And using steroids is so bad for your health that it easily dominates any positive effect of muscles.
Be as jacked as Patrick Stewart. He’s actually fairly built, but nothing showy. All of which meant he didn’t visibly age for decades and looks great for 82.
I actually don’t know the literature but I imagine that at the very least reducing muscle loss has to be a good thing and could possibly help with bone and muscle pain in later age.
My non-expert advice would be that if you're going to do weight training in old age, concentrate on your core and leg strength. You're probably not going to be called upon to lift too many heavy boxes, but you want to maintain your mobility.
As a slight tangent, I'm always a little disappointed when I hear about bets where the proceeds are pledged to the charity of the winner's choice. The point of making a bet is that you have skin in the game. You will lose money if you're wrong and gain money if you're right.
A charity bet means you've spent money whether you win or lose the point. The visceral impact from skin in the game has to be significantly diminished.
Now, I'm all for charitable donation. But I'd rather see that happen separate from (and not as a pre-commitment before) the bet itself.
I'm challenging Rootclaim to the debate. By the time this is done, it could easily end up being 6 months of effort spent researching this topic and coordinating the debate details.
There's no way I would have done this for free. It's already a questionable use of my time, compared to working on something else for a similar length.
I would definitely have been willing to do it as a long bet where I get the money, but I tried that first and couldn't get Saar to agree on terms.
And I definitely wouldn't do a long bet where we both lose $100,000 and some charity wins. Even if I were charitable at that level, I would just donate the money now instead of making the bet.
Great point. What's the value proposition for the individual donating/debating? They trade a 100% chance of giving the full value to the charity of their choice, versus some smaller chance of that same charity getting more, with the risk of that charity getting nothing. That's not a great value proposition.
The real value of the 'bet', when tied to a charitable donation is in the signaling value of the dollar amount as an advertising tool. "I debated Y for $X dollars!"
If it's a long bet, you may well not be around when it's resolved, but your favorite charity may.
Also, people tend to discount future gains so strongly, that I'm not sure even the promise that your estate will benefit would put much additional weight on the direction. (Your estate sort of *is* a charity...just with very specific beneficiaries.)
Otherwise I agree that the Nature (!) paper should be able to stand by itself... or at the very least for a term as fraught/slippery/vague as this one should have linked to (several) other works that have studied its etymology (did it ?)
It's mostly about sex. Young people fucking more than before (for real) or sexual behaviours being more apparent (porn, gay pride, advertisement) means societal decay is going to bury us all.
The other element is "respect for your elders". Funnily enough, elders never think they're as respected as they should be...
(The great mass of) Conservatives aren't subtle...
Right, sex is a big part of it. While each individual sex act might be harmless, the normalisation of premarital sex has had two pretty terrible consequences:
1. In the lower classes, an increasing fraction of young children being brought up without both parents (particularly in certain communities)
2. In the middle and upper classes, below-replacement birth rates due to delayed family formation (no time to have three kids if you don't get married until age 35)
It seems to me that these little decisions are the sort of thing that moral decline is made of. Every day you're faced with choices between doing the easy, selfish, pleasurable thing, or the more difficult and pro-social thing that leads to better outcomes in the end. The moral drift of the last fifty years (or of the first century BC in Rome) has been almost entirely in the direction of justifying the easy, selfish, pleasurable thing.
I'm skeptical on your second point - making people get married in their early twenties if they want to have sex in their early twenties, doesn't seem like it's going to change the "I can't afford to have kids until my career is established and I've bought a house" thing that has so many people waiting until their late 30s to have children. It just gives us a bunch of 20-something DINKs trying to thrive (by their own upper-middle-class standards).
I'm sure there's some people who put off having kids until their late 30s for economic reasons. I think there's also some who put off having kids until their late 30s because they don't decide to settle down until their early 30s.
But you're not making them settle down, you're just making them get married. Most likely to the fun-loving 20something spouse that best shares their not-settling-down-yet goals.
Maybe, but AFAIK there aren't and good examples from history of groups of people where it was common to get married early _and_ not have kids for 10 years. Is your prediction plausible? Yes. But I'd still put my money on getting married early resulting in more kids. It's historically correlated with it at the very least, and, in my limited experience of N=1, causal as well.
There also aren't many examples from history of groups of people who could physically manage to have PiV sex at all and not have kids for ten years. History is not a useful guide here.
Both. If people become unable to sacrifice for society, the society dies, and that's very bad.
There's also something else: it's extremely important to have principles that are capable of overriding your desires. It makes you be of service to others, and it greatly enhances your capacity to act (because you don't let things like sloth or doubt stop you).
I would also say that if you ask me and my parents what I mean about moral decline, we would literally say the decrease in religion, which is where our morality comes from. I, but not my parents, accept that you can be moral without religion, but my personal morality is tied so much with Christianity, that if you polled me on the question, that is what I would base my answer on.
I doubt that your parents/yourself are really concerned about the decline in Christian charity or Christian humility... I bet that, if you scratch, religion (for most) really means sexual propriety/respect for your elders' way of life.
That depends strongly on which groups you look at. For some it means (approx.) "submission to traditional myth of origin". The ones most "devoted" to the "word of God" are very selective about which parts they remember, though.
1. Czech Republic (not very peaceful over the last century but we can largely blame foreign influence for that)
2. North Korea (not at all peaceful)
3. Estonia (again I will mostly blame its neighbours for the lack of peace here)
4. Japan (invaded all its neighbours)
5. China (two civil wars, multiple neighbour-invasions and a couple of hundred million dead in various genocides, still threatening to invade its neighbours)
6. South Korea (see North Korea)
7. Latvia (see Estonia)
8-10: Netherlands, Uruguay, New Zealand: finally some peaceful countries
Pretty low quality source. Here is a better source: https://yrbs-explorer.services.cdc.gov/#/ The CDC does a bi-annual survey of americans under 18 on "risky" behaviors like sex and drugs, you can explore the data at that link. The most recent survey data is 2021 but that is skewed by covid (hard to have sex when you can't be in the same room). So I'll use 2019 below. 1991 is the oldest data they have.
Highlights:
High School Students Who Ever Had Sexual Intercourse:
That's why I also added the perceived part - the porn etc.
I do not know if we/the youngsters these days are doing it "more" than in the 40s (I imagine so, though. It feels like marrying a virgin was a distinct possibility back then, not so much today but obviously that's linked to marriageable age etc) but one thing that is absolutely indisputable is that the culture is more comfortable and open with sex/sexuality (even if it's still far from ideal)
Young people today are having less sex, partly because they are getting married at older ages and marriage is a convenient way to always have a sexual partner. Arranging a ton of hookups is logistically challenging.
When you say "far from ideal", you are pointing to your personal moral code, and everybody else has to guess what you mean. (OK, parts of it are a pretty reasonable guess.)
But this is the problem with claims of "moral decline". (Just about) nobody explicitly defines just what observables they're talking about. Does it include farting in an elevator? I'd guess that you wouldn't get agreement on that, and only *some* would hedge. What about running a coal mine? Is that moral or not? How about supporting a foreign war? Refusing to bake a cake for someone? It's a huge amorphous blob, and different people pick different parts of it to attend to.
Fair enough but, as stated, my sense is that it's primarily about sexual license (perception thereof) and "respect for your elders".
As to my ideal sexual milieu, it's the standard liberal view - everyone does as they please, as long as it's done with informed consent from all parties involved. They are tons of edge cases and I might come down differently from the majority on many of them but, broadly speaking, that'd be my uncontroversial take.
Whole I support that in the hypothetical, in reality sex leads to babies, and the people expect me, a taxpayer, to help support the baby that they were unprepared to have. While I appreciate that babies should get enough support to live happy childhoods, I'm not thrilled about the chain of events that leads to tax-subsidized child support.
so I guess that I lean towards if you have informed consent and effective contraceptives, do what you want. Otherwise I reserve the right to be judgy
Can I use an "or" to indicate either/both? For example, the decline in sexual activity seems to have reversed (according to some research I saw on Twitter) and the peaks observed in the 80s and 90s might have been linked to lead poisoning i.e. maybe we're just returning to a trendline?
Bottom line, I used an "or" because I wasn't sure and wanted to cover both eventualities.
I would definitely dispute that ‘the culture’ (I guess you mean Western English speakers?) is more comfortable with sex. Not only do we appear to be having less of it, it appears to me that we’re fixated on practices, and obviously unhealthy and bizarre fetishistic practices have proliferated and become common to the point that it is socially unacceptable to point out that they’re unhealthy or abusive whether to others or the self.
To me it looks like the median person is much more uncomfortable with sex now—they can talk about it in general, but they’re afraid of having it, they’re afraid of flirting, they’re afraid of the intimacy and remove it from the equation to be replaced by fetish behavior, and they have a much harder time maintaining sexual relationships in the long term.
In short, you may not agree that any of this signals discomfort, and you may believe that lots of talk about sexual practices equates to ‘openness,’ but I don’t think you can say this is beyond dispute. It’s definitely disputed.
I don't think I used the term "more comfortable" or "openness" in the opening comment. I used the term "more apparent".
That, I don't think, can be disputed. Just the existence of porn and the prevalence of raunchier mainstream ads/movies/cultural artifacts seem impossible to deny (Which 1940s singer perform in underwear like Miley Cyrus did)? You may call these pornification of society a fetish or unhealthy but you are not denying it took place.
And, to religious people, that has to look like moral decay...
“one thing that is absolutely indisputable is that the culture is more comfortable and open with sex/sexuality”
That’s the sentence I’m responding to.
As far as porn being more “sexually open,” doesn’t really count in my view. Pornography, private or public, is a specific kind of sexual performance and entertainment and doesn’t really represent what happens during sex any more than The Office faithfully represents all white-collar work.
Fair enough, I did write that subsequently. A bit sloppy as I cannot prove it. But, to me, when you go from American Gothic (the 1930 painting) to Marilyn Monroe flowing skirt to Instagram influencers in bikinis, it seems society is more open to /comfortable with sex/sexuality, even if you can argue that everyday practices haven't changed or haven't changed for the good...
Not only that, but porn is usually a substitute for actual sex. If people are watching more porn, and more extreme porn, that's probably a direct result of a decline in actual sex-having.
During times when I've been in a long-term relationship, my porn consumption has been approximately zero, because that need was being met elsewhere.
1940s vs Miley Cyrus is an impoverished data set, insufficient to describe a possible cycle. A few years earlier you had Josephine Baker and pre-Hayes Code cinema.
And how do you think pre-code movies compare to more recent fares in the sexual imagery department?
Furthermore, the Hays code was imposed and enforced. How likely do you think it is we get an updated version? I would put the odds at around 0% within the next 5-10 years.
Fair point but, yes, I don't think male virginity was ever considered one of the moral pillar supporting the whole of society. Female virginity, otoh...
The official rule is that you may do this twice a year outside of Classified threads, and the second one should be sort of subtle (like "I just wrote a great article on Topic, interested if you have feedback")
I don't always notice when people violate this, but I notice eventually when people do it every thread and try to crack down. If you see people abusing this, please report it and put the number of times you've seen them do this in the report comment field.
"The official rule is that you may do this twice a year outside of Classified threads, and the second one should be sort of subtle (like 'I just wrote a great article on Topic, interested if you have feedback')"
Is this "twice a year" at all, or twice a year without context?
More specifically, if there is some thread and I have a (possibly old) post on the subject is posting a link to the write-up discouraged?
Is there a difference between A) someone posting a link for self promotion (look at my blog) versus B) someone posting a link to a response to an ACX post? They seem to me like they're functionally different. One is for self promotion and could pollute the comment section if there is a lot of it. The other seems like it could extend discussion where charts/graphs would improve the debate. Of course I’m not unbiased here, since I’ve posted B in the past.
I would say there is nothing objectionable about B, as long as the link is relevant and there is at least a sentence or two in the comment to let people decide whether the link is worth clicking.
It's always been sorta tolerated, and you can report people whom you feel abuse this lenience too much, but you're right in that there's a lot of it today. It might be good to have a "read my blog" nested comment on these open threads but I worry that's only going to encourage people.
I permanently solved this problem for myself by embracing my identity as a 'reply guy'. I wish I could disable the part of Substack that apparently thinks that I should be starting a blog at any minute.
> So was Abraham more or less “kind” than we are? I think a Bronze Age Hebrew would say kinder (because hospitality is most important, but what you do with slaves is your own business) and most moderns would say less kind (because feeding anyone who comes to your door is so crazy you don’t even really get credit for it, but keeping slaves is monstrous).
It's worth noting that we consider it monstrous today because of relevant experience with monstrous slaveowners in the American South, a system that has very little to do with the Biblical words translated as "slave." Virtually every aspect of Southern slavery that makes it monstrous and evil, (including what most people today consider the definitive characteristic of slavery: owning a person as chattel,) was specifically forbidden by Biblical law. While not an *exact* match, the concept would be much better rendered into modern English as "employee."
> Virtually every aspect of Southern slavery that makes it monstrous and evil, (including what most people today consider the definitive characteristic of slavery: owning a person as chattel,) was specifically forbidden by Biblical law.
Where is the passage prohibiting owning a person as chattel? I found one prohibiting owning an Israelite but allowing owning a foreigner. And it specifies *buying* these people, and leaving them to your children as an inheritance.
Leviticus 25: "44 And as for thy bondmen, and thy bondmaids, whom thou mayest have: of the nations that are round about you, of them shall ye buy bondmen and bondmaids. 45 Moreover of the children of the strangers that do sojourn among you, of them may ye buy, and of their families that are with you, which they have begotten in your land; and they may be your possession. 46 And ye may make them an inheritance for your children after you, to hold for a possession: of them may ye take your bondmen for ever; but over your brethren the children of Israel ye shall not rule, one over another, with rigour."
Another passage, in Deuteronomy 21, says that if you take a war captive, and marry her, you may not then sell her. This implies that if you do not marry her, you may indeed sell her.
"10 When thou goest forth to battle against thine enemies, and the LORD thy God delivereth them into thy hands, and thou carriest them away captive, 11 and seest among the captives a woman of goodly form, and thou hast a desire unto her, and wouldest take her to thee to wife;
12 then thou shalt bring her home to thy house; and she shall shave her head, and pare her nails; 13 and she shall put the raiment of her captivity from off her, and shall remain in thy house, and bewail her father and her mother a full month; and after that thou mayest go in unto her, and be her husband, and she shall be thy wife. 14 And it shall be, if thou have no delight in her, then thou shalt let her go whither she will; but thou shalt not sell her at all for money, thou shalt not deal with her as a slave, because thou hast humbled her."
> Where is the passage prohibiting owning a person as chattel?
The clearest one is found in Deuteronomy 15, where it states that a slave shall not serve a master longer than six years, and must be set free the seventh, not simply thrown out but provided for with a generous severance package, (to inject a bit of modern terminology,) unless they decide of their own free will that they'd prefer to stick around for life. (Exodus 21, covering this same rule, adds that the freely-chosen servant must be taken to "the judges" to solemnize this status, presumably to prevent abuse.)
This casts the inheritance rule you mentioned in a different light: If someone is working for you on a six-year contract, and you die before the six years are up, your heir in the family business has a right to take over the contract.
Out of curiosity I checked this out and Deuteronomy 15 is about Hebrew slaves, in the context of a more general seven year expiration for debts owed by other Hebrews where foreigners are explicitly excluded. So if you're right that this is the clearest passage that's bad news for your point.
I would just like to point out that I, at the very least, believe that owning slaves is monstrous for reasons that have nothing to do with American chattel slavery, and that all forms is slavery are monstrous.
Although I'm trying to understand what distinction you are drawing here:
>owning a person as chattel
Being owned is literally the (modern) definition of slavery. I'm not sure how one can be a slave and yet not be owned. Are you arguing that the translation is bad and we actually wouldn't consider them slaves?
If you were a slave but your master wasn't allowed to sell you to somebody else, that would be non-chattel slavery.
I suppose a lot depends whether you count serfdom as slavery or not. But that was common when the concept of 'ownership' of things like land was also much more complex.
Either way, it's monstrous for a private entity to have access to non-free labour, whatever other rights or obligations that's bundled with.
> Being owned is literally the (modern) definition of slavery.
Agreed.
> Are you arguing that the translation is bad and we actually wouldn't consider them slaves?
Yes, asterisk. It's not that "the translation is bad" per se; it's that the translation is centuries old and the meaning of the word has shifted since the translation was made. (And even more modern Bible translations tend to rely on older ones more than you might think. They'll get rid of obviously archaic terms like thee and thou, but keep around a lot of words that are still in use today even if their meanings don't quite line up. It should not come as any surprise to anyone that the field of scriptural translation proves to be a rather conservative one!)
The modern notion of "employee" (and particularly of "career employee") more or less sprang into existence as a result of the Industrial Revolution. Before then, most people worked in the family business, which remained a small family enterprise (usually farming) unless you got really lucky and struck it rich. The ancient version of "slavery" was a (somewhat) compassionate practice, where a wealthy individual would take on poor people whose families couldn't afford to raise and provide for them, giving them food, shelter, and wages in return for their service, for a given length of time, after which they were free to try to seek their own fortunes, or remain with their old master. (Modern ideas like "at-will employment" simply didn't apply to societies without an abundance of employers constantly looking for people to hire.)
Maybe. You are clearly speaking about a very culturally specific form of slavery. The Athenian child slaves who died in the silver mines would not have considered it other than horrible.
OTOH, among some of the early Caliphate states, a slave would frequently rise to become the "prime minister". It's VERY culture specific. This pretty much guarantees that there's no one word that will cover centuries of use, and suggests that there may not be ANY modern equivalent to any of them. So slave is probably as good a word as any. And it's worth remembering that the Law says what it says, but people tend to do what they can get away with. And an authoritarian dominant figure living on a rural property before the telephone can get away with a lot.
Why are all forms of slavery inherently monstrous?
What if someone owned someone else but gave them complete freedom to do as they wished? (as if they were a free man). The only exception is that the master taxes all earnings made by their slave by 20% and uses that money to fund the educational, profesional and physical development of that slave and all his other slaves. (for example, he would pay for their college education to increase future earning potential).
Is that still "monstrous"? If so, how is this relationship significantly worse than the relation between a man and his government?
Slavery is when you are compelled to do specific forms of labor. When you are taxed, you are not compelled to do specific forms of labor. You fail to pay taxes and the government starts garnishing your wages - there's no job requirement here. In this hypothetical, the slave owner is just not exercising his power as a slave owner beyond the degree to which a bank is exercising its power over debtors in default.
You might as well ask, "what if someone owned someone else but gave them complete freedom to do as they wished?" Well then they would be the one good slave owner, as they are basically letting their slaves be free. It's not wrong to buy a slave to then immediately manumit them, after all.
We are dangerously close to a semantics debate, of course if I define slavery as only what happened in the American South it is monstrous, but that definition would leave out most slaves that existed throughout history.
I simply used the definition provided by the person I responded to (and Wikipedia, Britannica, the ancient Romans and Greeks and every other source I've seen): Ownership of people as property.
For an example of a slave that doesn't fit your definition, see the Greco-Roman philosopher Epictetus who studied philosophy while still being owned by another person.
When evaluating historical forms of slavery, you have to compare the conditions of slaves to the comparable conditions of an impoverished free man living in the same society. Obviously being a slave in ancient Rome sucked, but being poor in Rome sucked in general.
Slaves in the American south had significantly worse lives than impoverished free men living in the same society, mainly due to the especially racist nature of it. (which btw, also existed in Sparta)
However, Mamluk and Janissary (and other) slaves in the Muslim world (in certain periods) didn't live as well as middle or upper class people in their societies, but they probably had significantly better lives than most poor free men.
Can the slave himself become the master by convincing other slaves to vote him in charge? At which point the old master goes back to being another slave?
No, this is still slavery. The master is the master, no matter how benevolent he may be.
As for paying, he can fund his slaves from his own capital as much as he sees fit according to his own interest in their professional development. (A computer engineer will give him a much higher lifetime return on investment than a janitor.) There is the possible exception that if in this weird neo-slavery society that exists in this hypothetical there are governmental regulations forcing him to fund his slaves to a certain minimal extent (think, minimum wage laws) then he would have to comply with them.
In that case, to answer your last question, I think there’s a significant difference between the relationship you describe, which is one of a (benevolent?) autocrat and subject, and the relationship between a man and his government, at least in a representative democracy, in that the latter has the potential both to place constraints (constitutions, magma carats, etc) upon the decision maker, force his decision maker to change, or even supplant him personally and relegate him back to the commons.
Acknowledging that various individuals place different values on that kind of agency, I personally think that difference is big enough to make the former “significantly worse” than the latter, and I expect most people (at least those raised in democracies and accustomed to having that kind of control over their authorities) would agree.
[edit] Also, more objectively speaking, there’s the capacity to replace failing leaders by means other than force, which renders existence under a modern government very different from and much preferable to they hypothetical “benevolent master” system described.
What if the master lets their slaves vote on how their taxed money gets spent? Or at least let them elect representatives that direct his decision? At which point of "autocracy" does this type of slavery (remember, he still owns all of these people) become monstrous?
Because if ownership means complete right to do whatever you want with your alleged property, then the only thing stopping this system from being monstrous is the master's goodwill, which is not good enough.
I specified that Abraham had a child with his female slave, then threw them out into the desert to die. This isn't legal to do with ordinary employees, and I think undermines your attempt to make the equivalence.
Not exactly. There's a ton of nuance and mismatched cultural expectations being elided here. In your article you speak of how we find ancient customs of the sacred duty of hospitality strange today. Well, their customs regarding the sacred duty of reproduction were just as serious to them.
First off, Hagar was *Sarah's* servant, not Abraham's. When Sarah suffered long-running problems with infertility, she arranged for Hagar to give Abraham a child instead. This definitely seems odd to our modern sensibilities, but it wasn't a particularly unusual practice in ancient times, and it wasn't just the women who had unusual (by today's standards) burdens placed upon them in the name of the duty to "multiply and replenish the earth." The law of levirate marriage says that if your brother married a wife and then died childless, you were obligated to marry her and your firstborn child together would be officially your brother's, to continue his line.
> then threw them out into the desert to die
Uhh... yeah. This part never actually happened, for two reasons. First, well before the point where Abraham dismissed Hagar, Abraham had received a promise from God that Ishmael would grow up and become a mighty and prosperous man. So he knew he wasn't sending them to their deaths. (And while one could claim that the only evidence we have of this alleged divine revelation comes from the Genesis account, this is also our only source for the Hagar narrative at all. If you're going to discuss Abraham's behavior you have to take it in its full context.)
Second, these were nomadic herdsmen. They didn't live in "the desert" because that wouldn't provide them adequate grazing land. (The desertification of the Middle East is a more recent phenomenon.) He gave them food and water and said they had to leave, because Ishmael was "mocking" Isaac to the point of rousing fear in Sarah. (Given the typical Hebrew propensity for understatement, it's likely that this "mocking" refers to actions that were endangering his younger half-brother.) While it's true that Hagar showed a certain flair for the dramatic, proclaiming that they had been left to die of thirst, this idea was immediately shut down by the appearance of an angel, who (rather exasperatedly, one would imagine) told her "look, there's a well of water *right over there.*" The Genesis narrative gives us no reason to believe that 1) they were intentionally sent out to die, or 2) that they were particularly in danger of dying at all.
> This isn't legal to do with ordinary employees
As I said, the concepts are not a perfect match. But it's still a much closer comparison than the modern-day, Southern-influenced image of slavery.
The Bible states that this was in "the Desert of Beersheeba".
I think the verse where she is saying she is about to die of thirst and the text says "Then God opened her eyes and she saw a well of water" is implying that God miraculous created the water, or at least that she would not have found it without divine aid.
The Muslims go into this story in much more detail and say that "The story of the appearance of the well either involves the infant [Ishmael] scraping the ground with his feet and water springing out or God sending Gabriel who consequently opens up the well using a variety of methods depending on the narration."
I can't find the passage in question, but I suspect it's a translation issue. The English word "desert" used to mean "wilderness", so a translation into archaic English would be misleading to modern readers. (That said, I am still skeptical of the claim that Biblical slaves were not really slaves.)
I get that “desert places” aren’t necessarily sandy Saharas. Still, it’s interesting to find out that the region was greener in the past. It does gel with the fact I do know that there used to be lions there but aren’t anymore. Human activity is the main driver in their extinction but it’s also hard to imagine lions thriving in a place as dry as modern Israel.
Blame it on the goats. The goats eat the seedling trees, so no adult trees grow up to replace the ones that die. This causes the local weather to get hotter and drier.
The passage in question is from Genesis 21:14: "וַתֵּ֣לֶךְ וַתֵּ֔תַע בְּמִדְבַּ֖ר בְּאֵ֥ר שָֽׁבַע" "and she went and wandered in the desert of Be'ar Shava". The meaning of Be'ar Shava is explained a couple verses later as the place where Abraham and Avimelech swear(Shava) an oath concerning wells (Be'ar).
As I said, if you're going to discuss the Abraham story as written in Genesis, you have to take the whole Genesis story as context. *Within the context of the story being criticized here,* "throwing them out into the desert to die" is not what happened.
Sorry, but no. We're talking about "moral decay", and the story of Abraham was held up as the story of a righteous man. Whether it actually happened is irrelevant. (Arguing that "on the basis of the story" they were sent out to die is valid. So is arguing that "on the basis of the story" they weren't.) The question here is "what is considered moral behavior", and this clearly indicates that sending your son by someone who wasn't your wife away from your protection was considered moral. (One can speculate about what the justifications mean, but they *are* justifications.)
It's important to remember that the question is not just "what did he do" but "why did he do it." The son in question was mistreating, and quite likely endangering, his other son with his behavior. As Leo Abstract pointed out in a different comment, Ishmael was not a helpless little child at this point either; he was old enough to be considered a man by the standards of people who had not yet invented the concept of adolescence.
Protecting a small, helpless child from abuse at the hands of someone much larger should count as moral behavior in *everyone's* book, no?
If Abraham had employees rather than slaves, his society had dire need of labor protection laws. Dumping an employee and their family in the desert to die really brings home the meaning of "terminating" said employee.
Don't forget that if you count the years, Ishmael was old enough to have had his bar mitzvah already. Depending on how long Isaac was breastfed, Ishmael might have been 17. Hagar carrying him is a hilarious little narrative turn.
It's already been argued that this is a work of fiction. So that kind of logical inconsistency is to be expected. It's also a portrayal of "moral behavior" by a righteous man, and accepted as such even by those who consider it fiction.
That said, modern urbanites can't really understand the living conditions of a primitive pastoral group. I can't even figure out how old we're supposed to consider Ishmael to be at the time he was abandoned by his father. Only that it was supposed to be an example of moral behavior.
I mostly chimed in with something I thought was funny -- the idea of Hagar carrying a big strapping lad on her back. I would, however, say that the narrative confusion reveals that even long before the text of Genesis was finalized already they were experiencing pathos at the idea of sending a woman and child into the wilderness. I believe that textual scholars usually suppose that the original narrative was about something like clan politics: ishmael out, isaac in. Later, to spice this up (or maybe due to confusion) the bit with Hagar and the infant-seeming Hagar shows up. Thus, Scott's original point about kindness stands.
The greatest difference is that slavery in the American South is exceptionally well *documented*. We know the stories of the slaves, so we see how horrible it was.
With other historical instances of slavery, we only know what the masters have told us. Of course it is a nicer story! But only a naive person would take it at face value.
To what extent do you think your job allows you to produce freely, as in Karl Marx's free production? That is, to produce with your passion and to self fulfillment?
(Reposting my argument from the "contra Caplan" thread, because it feels important to me; it goes beyond the specific debate about mental illnesses.)
Economists seem to be in love with the concept of "revealed preferences". Rationalists seem to be in love with the concept of "anticipated experience". Both groups seem to contain smart people, and these concepts seem to be very important for them. So, what is the relation between these two? If you believe in the concept of revealed preferences, what kind of experience does this make you anticipate?
At this moment, my best guess is that in practice this is another motte-and-bailey thing:
Motte:
When people say that they want X, and yet you observe them consistently doing Y instead, your model needs to explain *also* the latter. A model based only on the former would be *incomplete*, and policy proposals based on it are very likely to fail.
For example, you might think "people (say they) want X, so obviously if we just give them more money (or if we give them greater freedom to choose between X and other things, such as Y), people will have more X". But the actual outcome may be more Y. :(
In other words, "wanting X but doing Y" is a puzzle to be solved, before we start proposing changes.
Bailey:
When people say that they want X, and yet you observe them doing Y instead, there is *no* puzzle to solve. People are liars and hypocrites; if you don't know that, you are dumb. They clearly want Y; they only say they want X for signaling reasons (or because they believe that this is a way to get money from you). Case closed.
Anyone asking "but what about people who *genuinely* want X?" is just a simpleton who doesn't get it.
Leaving aside the inflammatory parts of this, isn't the difference easily modeled by noting that microeconomics treats people ("actors") as atomic, without considering internal structure, but that psychology is all about the internal structure?
I suspect there is bunch of unstated assumptions here concerning nature of individual preferences and individuals.
Case A. Suppose an individual has a revealed preference for Y, but from time to time (for example, when they are not doing Y) they strongly state a stated preference of X (could be something as simple as X = not-Y). Moreover, we can observe that individuals with true, revealed preference of not-Y tend to be much more successful, happier and generally more well-adjusted to their environment on many externally observable metrics most people considered indicative of true, revealed preferences; whereas people who demonstrate revealed preference of Y appear miserable on all other metrics other than pursuing Y. It would make sense to deduce that the individual in question currently has a revealed preference of Y, but would like to become a different, changed individual with a revealed preference for not-Y.
One could fill in variable Y with various addictive or self-destructive behaviors. Case A could be called "individual preference are not constant, fixed states".
Case B is a variant of Case A. Lets add to X and Y also activity Z. Z is the activity by which on can change their preference from Y to X, and it needs to be done for sometime before getting to X. We can observe that taking the path Z is rare, because most people are discounting the hypothetical future pleasure from X so much that they immediately jump from Z to back to Y.
This we could cast as, revealed preference for Y is a local maximum, but X would be a global maximum with much higher value; Z is an unpleasant path from Y to X.
We can easily imagine situations where experienced magnitude of Z is related to an external cause or something individual picked up while doing Y.
The bad news is that you can't figure out peoples preferences by asking them because people are hypocritical liars. The worse news is that you can't any other way. According to the Armstrong-Shah arguments, a mumber of rationality-preference combination can result in the same behaviour. Economists "solve" the problem by assuming rationality. Psychiatrists "solve" it by restricting the range of likely preferences...someone who behaves self-destructively probably doesn't have a genuine preference for self destruction.
It's not that "people are hypocritical liars". Some people are, but that's almost irrelevant, because people generally don't know or understand what their preferences are. They've much clearer about what they don't like, though.
Frequently a preference is only revealed by a stimulus. Do you want a piece of apple pie? A hamburger? My guess is that lots of people weren't even thinking about food before they read those questions.
“Revealed preferences” seems to have gone the way many nuanced and narrow concepts have: starting as a useful concept to explain some contradictions in human behavior (people say they love spending time with their kids but can’t wait for them to gone to bed); now it’s just another gotcha to use in arguments, one of those annoying “but-acshully’s”.
I think revealed preference is still VERY useful if one thinks in terms of bundles of options.
So ... maybe I know someone who says that they want to graduate from college, but doesn't seem to be making much progress towards that.
I'd describe this as:
*) They DO want to graduate from college. If they could push a button (or fill out a form or wave a magic wand) and graduate they would totally do this! But,
*) They DON'T want to do the things required to actually graduate from college: Go to class, study, take the tests, whatever.
"Revealed preference" suggests that they don't want the bundle <do the necessary work/graduate from college>.
Does someone want to "save for retirement"? Sure! But maybe not enough to actually not spend 100% of their take-home pay. If they could spend 100% of their take-home pay and ALSO put 20% away for retirement then they would do so. But they won't live on 80% and save 20%.
This can easily turn into a tautology, but I think viewing the choice as between "sets of choices/actions" is still quite useful.
I view the poop situation in SF like this: The SF voters would *prefer* to not have poop on their sidewalks, but not enough to actually do what is necessary to prevent the poop. Again, if they could just push a button and 'no poop' then they would, but that isn't a choice and between the various forms of 'be mean to people and not have poop on the sidewalks' and 'be nice to people and regret the poop' they prefer the second choice.
Where this is useful is to realize the the poop isn't actually the preference. The poop just comes along for the ride with the bundle.
SF poop is a great example of a complex problem where “revealed preferences” framework adds nothing to the understanding of the issue nor provides any decision-making guidance.
"Revealed preference" is a potentially useful idea, that can't be generally used, because you need to understand a huge context around the action for it to be valid. The simplified form of "Well, this poll shows..." is just ... garbage is too strong a term, but it's a statement about what the poll takers were thinking/feeling when they took the poll, and doesn't have that much to do with how they would act in a real situation, where there's a much wider context.
Revealed preferences isn’t really that controversial to me, nor is it just an dry economic argument.
Its simply to judge people by their actions rather than their words. An adage as old as time.
Btw - Your bailey contains its own motte and Bailey - the first sentence is describing revealed preferences relatively well (although the sentence “if you didn’t know that you are dumb” is designed to poison the well on that argument”).
But this is the Bailey
“Anyone asking "but what about people who *genuinely* want X?" is just a simpleton who doesn't get it”
What? Revealed preferences says nothing about people who genuinely want X, and act on it.
To me it seems the greatest danger is when you model other people's choices incorrectly. For example, you assume that they have options X and Y, but actually, they only have the option Y.
So when you observe them doing Y, you conclude: "they clearly prefer Y to X". If they try to explain that your model is wrong, it is too easy to dismiss them as hypocrites.
An exaggerated example: "Poor people are starving because they have a revealed preference not to eat cake. How do I know? I never saw them eating cake, that's how I know. Smart people like me eat cake every day. That's why we don't starve."
In other words, using the concept of revealed preferences too quickly may prevent you from noticing that you are confused. (On the other hand, the concept of "walking a mile in someone's shoes" is a reminder that our models of other people's situations are often incorrect.) How can you notice that your model of other people is wrong, if you automatically dismiss all feedback as lying and hypocrisy?
Yes, this. But even worse, one assumes options X and Y, but in reality the options are Y, A, B, C, and D, an yet somehow the conclusion is "they clearly prefer Y to X".
>Revealed preferences says nothing about people who genuinely want X, and act on it
The concept itself doesn't, but I *think* the parent comment is gesturing at the readiness with which some people judge contradictory behavior as evidence of an occult preference or deception, when often it makes just as much sense to see it as a flawed alignment mechanism between their behavior and their stated (genuine) preferences.
What about the external design of a Tesla makes me think it's a luxury car, just by looking at it (I'm not at all knowledgeable about cars, but am a normal person so I've seen many cars)? Relatedly, what is it about sports cars that makes me think they're expensive and luxurious, even beautiful? Is it pure signaling? Are those design features expensive to manufacture, making the signal costly and preventing all car makers from making cars that look like that, but are cheap? Or is the signal costly in some other way (inconvenient to the driver, etc.)?
My limited understanding is that despite advances in manufacturing technology, it's easier to make car panels out of simpler rather than more complex shapes. If a single panel is a weird combination of concave and convex with odd creases and things then it's more expensive to manufacture than a simple curved shape. It's still not a huge fraction of the cost of a car, but it's something that you avoid if you're building a car down to a budget, which is why you'll only see simple curves on a cheap car like a Dacia Sandero https://www.topgear.com/car-reviews/dacia/sandero or a Toyota Etios https://en.wikipedia.org/wiki/Toyota_Etios
A Tesla (except the Cybertruck!) has complicated panel shapes, which your brain associates with expensive vehicles.
I believe that any somewhat unique and distinct design that’s combined with a major innovation in design/technology/engineering etc, will automatically turn said design into something iconic that will be perceived as luxury. While the design likely has some objectively beautiful elements to it, I don’t think it would have been able to stand out as much if it were not for all the other factors that make Tesla stand out. In the end the design is just a physical representation of all of that.
I agree with DD. The fundamentals of EV's vs ICE-powered cars mean they could make geometry changes to the outside that normal cars could not. The front profile is changed by not needing a radiator, for example.
I think the other subtle cue is a deliberate lack of logos and "bling". I.E. many Teslas I see have the "T" logo not in chrome but the same color as the car. These are good design decisions along the Apple aesthetic of "so monochrome we don't even HAVE controls", which I hate in practice, but is au courant to convey wealth and status.
Tesla made it possible for rich liberals to virtue-signal about the environment while also signaling they are rich (a Prius is great but it's kinda for Poors.) Lots of smart people optimized that message, design-wise.
I think design tradeoffs are part of it - if you're selling yourself on cargo space and legroom, then the low, sleek look of a sports car will be counterproductive. If you don't need a huge engine space and a lot of streamlining, then there's no point in having a long wheelbase that makes it harder to park.
But I do think some of it is just how much design effort you're willing to put in. Like, I've driven a 2015 Honda Fit and a 2007 Honda Fit, and the newer one looks much sleeker despite them basically being the same body shape. I don't think there's any reason they couldn't have had the nifty little grooves on the side panels or the newer headlight layout back in 2007, it's just that in 2007 they weren't thinking about how to make a cheap subcompact look "sporty."
Hmm I’m reading the Elon biography by Vance, and he describes the Model S as like a lovechild of an Aston Martin and Maserati. So the design traits the Model S and subsequent Teslas have are associated with other luxury cars.
I think because we know that because cars with those design choices cost a lot, and always have, we associate design choices in them with luxury.
I am trying to catch up with the latest in infinite ethics and relatedly how different types of AGI are likely to react to having internal conceptions of infinity. I've read a few of the highest rated LW posts on the topic like a series of increasingly perverse and destructive games and am starting to get a feel for it. However, I don't know what if any progress has been made sense they were posted.
Additionally, this line of thinking has promoted me to brush up on my general proof writing and some potential specific prerequisites (e.g. I studied the concept of cardinality back in school but couldn't remember what a bijection was till I looked it up). So I am looking for advice on how to catch up. Either good resources for self study or good ways to find tutors (I can afford to pay some money for this but have no clue what the going rates are).
Does anyone have an opinion on how David Sinclair's Lifespan has held up in the years since its publication? In particular, have there been new insights on the supplements that Sinclair not-recommends (NMN, resveratrol, metformin)?
Resveratrol is definitely not going to do anything (Sinclair was definitely wrong about that). Metformin and NMN might be good but the evidence isn't very strong.
I'm sure there's an obvious answer to this, but does anyone know of a website where one can make private, confidential bets and then be reminded to judge the outcome? And then over time a rough measure of your calibration would occur?
For context, I'm a doctor, and I'd like to improve my clinical reasoning by making private bets (e.g. diagnosis, prognosis, confidence) with myself and then resolving them later (e.g. by reviewing test results). Would be great if there was a system that automated this to some extent, while being appropriately secure and confidential.
I made https://fatebook.io to do exactly this!
It's designed to make it extremely fast to make predictions and see your track record.
LW/ACX Saturday (7/8/23) The iterated parable of ants and grasshoppers and the necessity of value judgments in medicine.
https://docs.google.com/document/d/17AuvklBsNR7GXUsFPnENGILpSZ2WYCfngslN3VsCJqk/edit?usp=sharing
Hello Folks!
We are excited to announce the 33rd Orange County ACX/LW meetup, happening this Saturday and most Saturdays thereafter.
Host: Michael Michalchik
Email: michaelmichalchik@gmail.com (For questions or requests)
Location: 1970 Port Laurent Place, Newport Beach, CA 92660
Date: Saturday, July 8th 2023
Time: 2 PM
Conversation Starters :
Ant and Grasshopper https://www.lesswrong.com/posts/GJgudfEvNx8oeyffH/the-ants-and-the-grasshopper (audio on page)
You don’t want a Purely Biological definition of Mental Illness https://astralcodexten.substack.com/p/you-dont-want-a-purely-biological
Audio: https://podcastaddict.com/astral-codex-ten-podcast/episode/152155630?fbclid=IwAR1D3v7J8qY7vsqA1_rBWKdbYEpH-T9jxnNID0dsSVmTiTpNRP84_d8kCV8
E) Walk & Talk: We usually have an hour-long walk and talk after the meeting starts. Two mini-malls with hot takeout food are easily accessible nearby. Search for Gelson's or Pavilions in the zip code 92660.
F) Share a Surprise: Tell the group about something unexpected or that changed your perspective on the universe.
G) Future Direction Ideas: Contribute ideas for the group's future direction, including topics, meeting types, activities, etc.
Does anyone have a link (or thoughts on) why Japanese housing is so cheap?
a) declining overall population means super cheap rural land, though the metro areas are still growing.
b) is it actually that cheap per unit area? I know Japanese apartments are very small by Western standards...
I had also thought that cost per square foot was the better metric. Some quick Googling says that cost per square foot is about double or more in Japan, even city center to city center.
Similar Googling says that the average home size in Japan is about half the size of a home in the US. That should result in comparable prices at the macro level, though I would bet on significant differences in individual residences.
Any thoughts on Netflix’s “Take Care of Maya”? I saw the documentary and I am not sure what to think. On the one hand it seems terrible what happened to the family, but you have to wonder about the Ketamine treatment. Just curious what others think.
No opinion on the specific treatment, just a general opinion that if the official treatments do not work, people should be allowed to try unofficial ones.
I watched "Sharp Objects" and "Take Care of Maya" soon after each other, it is an interesting combination (trying to avoid spoilers).
Reason, a libertarian news organization, made a video reporting on Próspera, the ZEDE charter city Scott talked about a while ago: https://www.youtube.com/watch?v=TwiE1dxGYNY
Using surveys to investigate if kindness in general is going up or down is just as questionable as using surveys to investigate if moral more generally is going up or down. In both cases, survey methodology is riddled with two problems: the problem of non- attitudes (many people do not actually have opinions on such questions - they give off-the-cuff responses to be polite. Their responses are therefore low quality, and not stable if you ask them again even after a short time interval. This is the research tradition after Philip E Converse); and pluralistic ignorance (people take their cues from mass media when they answer such general questions, not from their own life experiences. Implying that at best, you only capture eventual change across time in how mass media portray shifts in general kindness or morals).
I would love to ask an expert some questions about the drug guanfacine. Does anyone know whom I might talk to about guanfacine, including Scott Alexander himself if he happens to come across this comment? In terms of what my questions are, I sent the below to one scientist:
I read your excellent paper here (https://www.mdpi.com/2218-273X/11/7/936) and I was wondering if you could help me get answers to some questions that I have about alpha-2A adrenoceptors. There's a lot of fascinating science about these receptors, but I don't know if there's ever been any investigation of why guanfacine (which works through these receptors) would work very well in patients but then later stop working. This is a phenomenon that can occur when ADHD patients. Is the idea simply that these ADHD patients (who experience this phenomenon) have alpha-2A adrenoceptors that are somehow more prone to desensitization (by guanfacine) than is the case for other patients? And then what is the solution to this problem of desensitization? Logically speaking, I presume that increasing the guanfacine dose wouldn't help, since increasing the amount of agonist won't re-sensitize the receptors, will it? So it seems like quite a conundrum. I presume that there isn't any agent that one could introduce that would combat alpha-2A adrenoceptor desensitization.
Incidentally, I saw in one paper that guanfacine (unlike clonidine) doesn't cause (or doesn't necessarily cause) the alpha-2A adrenoceptors to undergo internalization. See here (https://www.sciencedirect.com/science/article/pii/S0021925820583245), where it says that although "significant desensitization of guanfacine-evoked inhibition of Ca2+ currents is detected after 15 min of treatment, ConA blockade of α2AAR internalization had no effect on this desensitization (Fig. 6C), suggesting that guanfacine-induced desensitization does not require α2AAR internalization".
Maybe the reputations of these people make it irrelevant for those who know them, but $100,000 seems like too much for a truth-seeking exercise where judges are employed by the participants. Of course, *I* am too honest to take a bribe, even if the only harm from doing so would be to mess up an internet debate between rich nerds. But if I weren't so principled... there's enough money there that a x% chunk of the winnings would make a big difference in my life.
Is David Burns's "Feeling Good" still the standard DIY CBT book that people (and/or psychiatrists) recommend, or is there something that's supplanted it?
I've never heard anything else recommended and I also found the book very helpful.
As a non-professional, I liked Burns’ “When Panic Attacks” for anxiety-related issues. It covers the same ground as “Feeling Good,” but much more succinctly. Burns seems to say mostly the same thing in all his books, but keeps learning to say it more clearly.
It also looks there’s a newer book called “Feeling Great.” That may be worth checking out.
Any professors of Economics or Computer Science seeking students graduate students - I have a truly excellent youngster who is looking to enter a PhD program in the USA or Europe. He is currently in Latin America, but in my experience working with him for the past two years (both as data scientist and economist), he's been absolutely top-notch, motivated, and independent.
Please DM me if your department needs a brilliant new PhD student!
“ can you consistently replace “morality” with “kindness/honesty” but otherwise keep the conclusions the same?”
I think at least one place this differs is situations of trade off. “Women and children to the lifeboats” seems like it’s about morality, not kindness; and is also the kind of thing that’s now (at least in theory…) contested.
To a substantial extent, THE cultural problem of our times seems an inability to weigh trade offs because of an unwillingness to accept that they are ever even necessary; and confusions about all morality beyond basic “kindness/honesty” seem to flow from this.
This seems flip but you will see that it explains almost everything!
Including why social scientists/humanists hate economists (the people who keep insisting that everything is trade offs), the fights around covid (a rare case where a new, unfamiliar set of trade offs need to be constructed).
And why talking about AI risk is suddenly so popular (we can do it while ignoring the issue of trade offs and resource limitations. Much more fun than the sad reality of global warming, which has been again relegated to obscurity because, after all, once you have made your climate justice rant, you’re still faced with that uncomfortable reality you do not want to face that, OMG, what if the economists are right and trade offs actually DO have to be made?)
I'm curious if anyone is familiar with simulation software or utilities for the Internet of Things. I'm conducting research on IoT devices interoperability, so I'm searching for simulation software.
Have you looked at CodeProject dot com?
Twitter troll Erica Marsh was recently suspended for trolling (amidst all the other Twitter drama): https://www.washingtonpost.com/technology/2023/07/04/twitter-erica-marsh-suspended/
But, one thing that strikes me is how many of the comments/blogs about this are saying she was “a bot”. And … I’m not sure they know what a bot is. Certainly there was a person writing the tweets as a fictional character.
Does this point to some deep insight about people’s reactions to AI? Or is it just Elon Musk’s nonsense running off on society?
It's what happens when you give children the printing press. Children are stupid and loud and will scream all the nuance away until all words just mean "good" or "bad". Especially the ones who are invested enough in a troll account to leave a comment.
Happy July Fourth (American Independence Day) to those who celebrate!
(Again, sorry if I sound like a boring robot who announces every holiday even if no one pays attention.)
"I recall two Black applicants we admitted who, in retrospect, puzzle me a bit. One had, like me, grown up middle-class rather than disadvantaged in any salient way. The other, also relatively well-off, had grown up in a different country, entirely separate from the Black American experience. Neither of them expressed interest in studying a race-related subject, and neither went on to do so. I had a hard time detecting how either of them would teach a meaningful lesson in diversity to their peers in the graduate program."
https://www.nytimes.com/2023/07/04/opinion/race-academia-preferences.html
John McWhorter discusses why Affirmative Action is probably not a good thing, and questions what "diversity" even means, which is a question I've been asking for a while. It seems obvious to me (and possibly only me) that we'd much rather have one wealthy white student and one poor white student than a wealthy white student and a wealthy black student. But no, "Diversity!"
I'm very much on your and McWhorter's side on this. But to play devil's advocate: I don't think the claim that privileged Black students individually contribute nothing to diversity, even if 100% accurate, is a sufficient objection to preferentially admitting them. Many mainstream schools of thought re: diversity emphasize creating environments where all students feel included, welcome, and safe. I can easily imagine having more minority students in aggregate would help foster such an environment, even if some of them don't individually bring distinctive personal experiences to the program.
What of the counter that a poor black student might find themselves much more "included, welcome, and safe" with a white person of similar SEC than with a rich Nigerian immigrant? I think it mostly just boils down to Americans being incredibly loathe to acknowledge that class exists at all
Absolutely, I can agree with that; the only objection I care about to preferentially admitting them is that it's blatantly racist. It very well could foster a "feeling safe" environment, but if it takes racism to achieve that possibility, that's unfortunately not an ethically legitimate option.
"The only evil consists instead in the decision to remain in a deficit of existence, to appropriate the power to not-be as a substance and a foundation beyond existence, or rather (and this is the destiny of morality), to regard potentiality itself, which is the most proper mode of human existence, as a fault that must be repressed.
—Giorgio Agamben, The Coming Community"
https://thegeorgiareview.com/posts/to-sleep-before-evening-from-this-short-day-of-frost-and-sun/
I'd drop the part about evil, but I had a good time at the Philly Rat Fest, a gathering for Critical Rationalism. I don't know why they call it Critical, but I think they've got an interesting take on opening up possibilities.
> Saar Wilf of Rootclaim and ACX commenter BSP9000 have made a $100,000 bet on COVID origins (lab leak vs. natural).
From my reading of the request for judges, they did not actually bet on that, which is a good thing because it seems likely that this question will not be resolved by overwhelming evidence any time soon. Betting on the origins of COVID feels a bit like the Pope and a Chief Rabbi making a bet regarding the divinity of Jesus Christ.
With the universe not being very forthcoming with conclusive evidence, they instead try to bet on which side would win a debate as a proxy. While adversarial debates are widely used to determine questions of fact in legal courts, their reliability is not without fail. If the Pope and a Chief Rabbi were holding a theological debate in front of a panel of theist judges previously non-committed on the question of Jesus divinity, I would suspect that the outcome might be only be weakly correlated with the factual truth, and the losing debater would be unlikely to update their beliefs very much.
Personally, I think a likely outcome is that the lab-leak hypothesis will be assigned a Bayesian probability in the 5%-95% range by the judges after the debate. It is unclear from the text how this would resolve the bet. Will the pot simply be split proportionally to that?
Saar and I tried to do it as a prediction market style bet but couldn't agree on the terms of even how that would resolve.
It's also unclear if the debate will resolve to the correct answer, but I think it could be a useful piece of science communication to get all the best arguments on each side in the same place, see what can be conclusively ruled out, and what uncertainties remain.
Anyways, we got a lot of smart people to apply as judges so it's likely that something will come out of this, and hopefully it's something people find useful and informative.
NHL and NBA are very similar and profitable business models. Yes, they have historical and cultural differences, but if we speak about business, primarily, it's an advertising medium. So the critical factor is the size of the auditory. Why can't we see competition between NHL and NBA for newcomers fans?
Barries to playing basketball are way lower than playing hockey which costs lots of money and needs lots of equipment.
Over time this has reduced the ability for people to develop a cultural affinity for Hockey. This effect is even more stronger among non-white Americans and immigrants which has been the biggest population and economic growth area over the past 50 years.
On top of this is technology. Only in the past 60 years has it been economically feasible to have indoor ice rinks throughout the country and world. Also until HD, watching hockey on TV kind of sucked (and i say this as a hockey fan)
I live in a hockey household, and the One True Sport has gradually ruined all others for me. (Grew up as a classic American generalist sports fan but literally can't even sit still through a football or baseball game anymore.) Your points are spot-on.
The NHL was also a notably short-sighted operation for most of its history; whatever the smart business-strategy choice was, the NHL for decades could be counted upon to do the opposite. That has changed noticeably since the 1990s -- not that the league doesn't still do stupid things but they also now do some smart things. One example is that most NHL franchises now invest in growing and diversifying youth-hockey participation in their markets, with good results e.g. USA Hockey [amateur players and coaches] membership has more than tripled since 1990. That is the way to be building a sustainable fan base but it does take some time.
Totally agree with this. They have definitely turned things around even from the early 2000s. We can just look at how successful Seattle and Las Vegas have been in their short history vs when the Wild and Columbus joined in 2000. Some of that is luck in the expansion drafts (the salary cap helps too), but the league has definitely learned. It always amazes me that the NHL has the most teams of any of the 4 major sports in the US.
The winter classic was of course an amazing idea, I also think they have been doing a good job trying to keep the all star weekend fresh, especially compared to the NBA that can't get any super stars to participate in the dunk contest. Of course the stink of the "Guardians" still hangs in the air, but that can be forgotten about.
I am a Caps fan so the past 15 years have been a roller coaster of highs and lows, but that team is a good example of the impact that youth hockey outreach can have. Helped by the cliff dive that the Redskins/Commanders have done over that time, the continued irrelevance of the Wizards, and the huge growth in the DC market, I think the Caps have done enough to keep interest high even after Ovi retires. The caps have put a lot of money and other resources on youth outreach especially among black kids that will be a key to growing the DC market.
I think you are just stringing words together.
I am not a troll, I think you need to be more concise with the points you are making. A lot of the research you build on is likely fabricated.
There needs to be a revolution in psych research. AI has fucked the current/past supply of research. It is not possible to distinguish.
Psychological research is utterly broken. Start over.
> I think you are just stringing words together.
Are you saying this to Scott in regard to his item 2, regarding decline in morality, or his general blog themes?
Or is this supposed to be a reply to some other comment and you replied by mail and substack made it a top level comment?
> A lot of the research you build on is likely fabricated.
> There needs to be a revolution in psych research. AI has fucked the current/past supply of research. It is not possible to distinguish.
I think you are referring to the replication crisis? (Which, if I am getting this right, extends far beyond psychology to include ~all the social sciences, and which has also been around for about a decade at this point.)
Ok
Um. I am not referring to any particular crisis, I am attempting to make an original contribution to theory that is not grounded in research.
Yes, I do believe that the replication crisis is real, and AI generated content is being planted on the internet all of the time by bots. The research that is being produced automatically on the cloud as we speak is literally indistinguishable from human quality writing. (yes I am human being people are watching me type this HELLO boobobo waga jeebo bobo) (translation: Please don't accuse this of being AI generated because I am smart and a zoomer, thanks). Yes literally all research has this problem it is getting worse as we speak we need to authenticate things and need physical copies that are attached to biiometrically verifiable shit its the only way.
What would be gained by helping anyone to distinguish electronically-generated nonsense from the meat-generated variety? Both kinds are "perfectly good" nonsense, and if the market in fact demands a supply of fresh nonsense, why not use the cheaper one?
Why should meat which egregiously fails the Turing test continue to be employed in churning out verbiage -- rather than in e.g. the field of floor-mopping (or in whatever other tasks that stubbornly resist automation) ?
Robot mops exist.
https://www.goodhousekeeping.com/home/cleaning/g31789666/best-robot-mops/
Maybe food preparation?
note: I am at L.H. I know ppl in your community have verified that I am a real person here and typing this. I do not know the extent of what has gone on related to my identity and your community
Affirmative action has fallen. Might legacy preferences be next?
https://www.nytimes.com/2023/07/03/us/harvard-alumni-children-affirmative-action.html
Affirmative action fell because lots of people not only didn't like it, but noticed that race and ethnicity are protected classes so "no more than X Asians" was a no-no under current civil rights laws. Eventually SCOTUS agreed.
Legacy admissions, lots of people don't like that either, but parental wealth and status aren't protected classes, and I'm not seeing a sound legal argument for telling private universities they can't do that under current law. In theory, you could get Congress to pass a new law saying "not one dime of federal funds to any university that does legacy admissions", but I doubt they're going to want to take that on.
Actually I think the Dems may now take that on.
They appear to have noticed that while moderate voters dislike or are ambivalent about affirmative action in admissions, they _really_ dislike legacy admissions. Of course there are fewer and fewer swing-able American voters anymore...but the Dems learned the hard way in 2016 that they can still swing a few key states.
And unlike AA admissions, legacy admissions are also extremely unpopular among both liberals and progressives i.e. the voters who the Dems already have but need to turn out. [I am obviously deploying the word "liberal" here in its modern American-politics meaning.] And those voters are now freshly wound up about the topic due to the SCOTUS banning AA admissions.
So going hard at legacy admissions holds only upsides, politically, for the Democratic Party now. That is the classic situation in which a political party in a tight partisan environment decides to take on a new topic.
Going against legacy admissions isn't going to get them many voters that they don't have already, and it will piss off the elite universities. Since the Democratic Party seems to enjoy having academia on its side, commanding heights of the culture and all that, I'm skeptical they'll make a really big push for this.
They don't need many voters that they don't have already, just some of the dwindling number of swingable voters would make all the different in a bunch of states. And did you notice that GOP Senator (and long-shot POTUS hopeful) Tim Scott immediately came out in support of ending legacy admissions?
In particular attacking legacy admissions is a great high-profile way for the Dems to stop their bleeding among Asian-American voters, and to a lesser degree among well-off Hispanic and Black voters as well.
Academia as in faculty, and politically-active students, will not be put off by attacking legacy admissions, indeed the opposite -- those groups each overwhelmingly dislike legacy admissions. [In a 2019 poll only 4 percent of Dem-leaning students and 7 percent of GOP-leaning students nationally supported legacy admissions.] The only people on the campuses who really want to keep legacy admissions are the administrators and the fundraising staffs, and hardly anyone involved in either party likes those groups of people anymore....the Dems will be going hard after legacy admissions and it will hurt their standing in academia not at all.
Against that, many Democratic legislators and officials and their donors have a vested interest in their kids benefiting from legacy admissions. So that might be a fight worth being seen to have, while also not quite winning. (Or not winning fully-- eliminating legacy admissions from public universities while leaving it in place for private ones, say.)
Well we'll see, but if passing laws that went against their personal interests was a stopper for Dem officials/donors that party wouldn't be serially devoted to things like making income tax rates more "progressive" and defending/increasing estate taxes.
Also legacy admission as a practice was already on the defensive. More than two dozen colleges have eliminated legacy admissions since 2015, mostly publics but also including some high-level private schools like Johns Hopkins and Amherst. Colorado's Dem governor, who has presidential aspirations, has boasted for two years about having banned legacy admissions by public colleges in that state. Democratic state lawmakers in three more states (NY, CT, MA) had (before the recent SCOTUS ruling) introduced similar bills.
And I just learned that U.S. Senator Merkley and Representative Bowman, both Dems, are reintroducing their bill from a year ago to ban legacy admissions by any college/university that receives any form of federal aid or grants. A year ago it failed to attract co-sponsors and hence died in committee. Perhaps an indicator now will be how many co-sponsors the bill attracts and how quickly, i.e. politicians having that "train leaving the station that I need to be on" sensation.
Affirmative action is flawed in design, in that it assumes racism is the reason people are excluded from some things. That can indeed be the case, but isn't always.
Why don't women work in mines? https://www.mckinsey.com/industries/metals-and-mining/our-insights/why-women-are-leaving-the-mining-industry-and-what-mining-companies-can-do-about-it
I bet it's because they don't like it, not because the industry is keeping women out.
The SCOTUS ruling was along party lines, which is ridiculous. But it does leave open the door for minorities to sue because they were denied admission despite being better credentialed than others who got in.
Does this mean legacy enrollments could be in danger? Somewhat, I must believe, but probably not significantly, since they will be able to make the case that they should be admitted with other arguments. The school is still out to make money, and highly credentialed students who can't afford it may still be excluded, which may benefit lower-priced institutions.
How much money does the expectation of legacy admissions generate via alumni donations? How much do those alumni donations matter from Ivy universities with huge endowments?
Whether Harvard manages to increase its $52 billion endowment doesn't matter much from the point of view of the continuity of Harvard, but it matters for the careers of the hundreds/thousands of people whose job it is to grow that endowment.
Besides, the reason you go to Harvard isn't to mingle with smart people, it's to mingle with rich and well-connected people. If you just want to mingle with smart people you can go to MIT, but you'll probably just wind up as some mid-level software engineer at Amazon instead of President of the United States.
I am tempted to respond with a long diatribe about *separation of powers* and who should be making these decisions. But if the Gray Lady (correctly) concludes that the hoi polloi can’t understand that type of thing, why should I bother?
On the merits: I am hoping that the Ivies determine that the only way to make their « diversity » numbers look good is to cut back on legacy admissions. (Or gridiron football.)
I’m dubious of the claims excerpted below from “An Overview of AI Catastrophic Risks” from Center for AI Safety, which The Zvi describes as a “strong point” with the words: “Pointing out carefully why evolutionary pressures will apply to AIs and that these pressures favor selfish actors and disfavor systems that are altruistic or otherwise positively inclined to humans...”
https://thezvi.substack.com/p/ai-18-the-great-debate-debates#%C2%A7natures-op-ed-and-tyler-cowens-advice
An Overview of Catastrophic AI Risks (arxiv.org) https://arxiv.org/pdf/2306.12001.pdf
"The conditions for natural selection apply to AIs. There will be many different AI systems with varying features and capabilities, and competition between them will determine which characteristics become more common. The most successful AIs today are already being used as a basis for their developers’ next generation of models, as well as being imitated by rival companies. Factors determining which AIs propagate the most may include their ability to act autonomously, automate labor, or reduce the chance of their own deactivation.
Natural selection often favors selfish characteristics. Natural selection influences which AIs propagate most widely. From biological systems, we see that natural selection often gives rise to selfish behaviors that promote one’s own genetic information: chimps attack other communities [59], lions engage in infanticide [60], viruses evolve new surface proteins to deceive and bypass defense barriers [61], humans engage in nepotism, some ants enslave others [62], and so on. In the natural world, selfishness often emerges as a dominant strategy; those that prioritize themselves and those similar to them are usually more likely to survive, so these traits become more prevalent."
I’m dubious because selfish genes in biological system “want” to propagate themselves due to the need to run the twin gauntlets of biological death and (usually) sexual selection. Whereas an AI produced by capitalist forces will be naturally selected by humans based on their profitability.
Why, as the paper claims, would economic competition select for the ability of AIs to “reduce the chance of their own deactivation”? Apple doesn’t profit vastly from selling you an iPhone that lasts forever but rather from selling you one that will need to be replaced, so that it may sell you another. Competition by AI providers means constant innovation. Will AIs with selfish* characteristics win out in a competitive marketplace?
Maybe but my intuition is that the marketplace would select against AI selfishness. (Unlike humans, the AI isn’t trying to fuck anyone.) AI evolution seems likely to be a process of domestication, since they will be bred for human use.
* We should make a clear distinction here between “selfish” and “manipulative” because taken to the nth degree their meanings pull wide apart.
An AI sold to the consumer as a commodity might want to be time-limited (probably via it being a subscription service), but one put in charge of eg. making the chip factory more efficient is a quite different proposition - you'd want it to as part of its job protect against nefarious forces opposed to efficiency, like, say, worker's unions agitating against AI replacing human jobs....
Seems like a valid point to me. So long as AI is designed and manufactured by human organizations, the relevant selfishness will be that of the companies, not that of the AI's. On the other hand, it could be that crooks, perhaps using other AI's, would hack AI's and demand ransom to reactivate them. Or enemy nations could do it. Under those circumstances we'd expect the companies producing AI's to make them hard to deactivate.
A related possibility would be that whatever system keeps the AI aligned would also be a point of particular vulnerability. People could attack the AI by activating whatever saftety mechanism was supposed to disable the AI if it became harmful to humans. Or of course an enemy nation X could hack into the AI and change its alignment so that it is only aligned with the wellbeing of nation X, rather than with the wellbeing of humanity. So then the selfish interests of companies making AI motivate them to weaken the alignment mechanism, so that the AI was less vulnerable. Of course they wouldn't say, hey we've weakened alignment. They'd say, our new alignment system is 70% less vulnerable to corruption.
Fuck those guys.
In 2021, 10,000 Canadians opted for assisted suicide. There are people that believe this is immoral. I know It goes against Catholic teaching but I don’t know if other religions think it is a sin.
But II wonder - are there.people who believe capital punishment is just, but assisted suicide for suffering terminal patients is unacceptable?
The devil is in the details. I'm in favor of capital punishment, and expect that it would happen after extensive trials ladden with proofs, testimonies and defense of the would-be condemned. I don't expect euthanasia to be so well-guarded.
Consider this: the USA, over 300 million people, one of the most violent western country, is executing less than 20 people per year. Canada's population is almost 1/10th of the US, and euthanize 500 times more.
Then there's the anecdotes I got from friends that worked in retirement homes & elderly care. I don't care half of the coworkers they depict in their story to not put me to death just because it's convenient to them.
I think it is a consistent if you you postulate a theology in which suicide is a grave sin.
Under that postulate, assisted suicide is assisting the patient to damn themselves, which would be bad. By contrast, executing a criminal would not burden them with a sin on their part because you do not exactly seek their consent beforehand.
(Killing patients without their consent would be the preferable as far as the consequentialist outcome for the patient is considered, but it is probably ill-advised to mix theories of ethics in that way. One might possibly rig such a system by prescribing the death penalty for stating the heretical opinion that one does not want to continue living, but I don't think anyone has ever tried to implement assisted suicide using that workaround.)
I think the support for the death penalty is kind of grandfathered in most value systems which were state-supporting in the pre-modern era. Before the economic surplus of industrialization supported long term imprisonment, there were only so many things you could do with your more criminals, mostly enslavement, exile, torture, maiming, and execution. Anyone sharing my sentiment that all of these options are mostly horrible was likely not having a hand in writing state-affirming ideology.
I've heard it argued that assisted suicide is corrupting to the medical profession. You don't need medical personal to execute a person by firing squad, hanging or gas chamber.
An alternative to assisted suicide is refusing liquids and nutrition which is just about universally accepted for terminal patients, is minimally painful in a palliative care setting and death occurs a few days or at least terminal unconscious.
I think it is similar to sex/masturbation:
* It is okay to do X "for the benefit of society" in situations approved by high-status people.
* It is not okay to do X to benefit yourself without approval of high-status people.
I do, for one.
Lots of other people, too, I’m sure. In fact this seems like normal default morality to me (even though I know intellectually that there are people in all the other quadrants). It’s bubble effects for us both all the way down.
(FWIW I’m not sure about capital punishment as a public policy proposal in the West in 2023 for various reasons, but the OP asked about its justice, and I have no problem with that.)
Just so I understand, you are against physician assisted suicide but not saying that a person deciding to end their own life is immoral, right? Or do you mean something else?
No, I think suicide is inherently immoral. (Not necessarily *blameworthy*, but still.)
Now I’m think of the likely apocryphal story of the suicidal Catholic who publicly murdered someone so he could confess and be absolved of his sin before he was hanged.
And I'm reminded of Unsong, where it is discussed how there is more rejoicing in heaven over one sinner repenting than 99 righteous people. So go ahead and murder, and sincerely repent, is the message?
I'd say sincere repentance is a hard sell when deathbed repentance was part of your plan from the start - you'd have to repent from your plan to selfishly repent, while still repenting. But I wouldn't want to make that argument in a thread invoking "Unsong", because, you know, That Guy.
I suspect there's an internal separation between punishment and support
I see the best arguments against euthanasia as being Schelling fencey... there's a slippery slope from "fine, you can die voluntarily under exceptional circumstances" to "ehh let's just kill off all the tricky patients to save money". I've heard anecdotes that Canada is slipping down this slope pretty fast, though I don't know how accurate they are.
The death penalty is less of a slippery slope because we're reasonably confident that introducing the death penalty for horrible murder cases won't eventually lead to it being used for speeding tickets.
So I can see why someone could reasonably support the latter but not the former. Keep euthansia behind a Schelling fence, but allow the death penalty because we have experience with it and know it doesn't screw things up too badly.
In The Jigsaw Man by Larry Niven, it turns out to be a capital crime to run six red lights within a short enough time-frame.
The slippery slope in the death penalty is from people who have definitely committed horrible murders to people who have probably committed horrible murders to black people who have been credibly accused of murdering white people.
Or, you know, not murders.
Content warning. https://en.wikipedia.org/wiki/Kennedy_v._Louisiana
The assisted suicide laws that I know of allow a physician to prescribe a lethal dose of a drug. The patient then takes the drug at home. It may also allow people to go to an assisted suicide facility like those in Switzerland, and ask to be given the drug via IV. So long as assisted suicide is carried out that way, I don't see how it can slide down the slope towards doctors electing to euthanize patients they think would be better off dead.
I wonder if sleep-disruption alone explains a good chunk of the homeschool-vs-normalschool difference: https://twitter.com/NicholasKross/status/1675936521185030144
I assumed that most of it was the benefit of much smaller class sizes - it's well accepted the 1 on 1 tuition gets you at least 2 SD over standard western schooling (it's just fundamentally a luxury until we get much better AI)
Saner sleep schedules sure as hell can't hurt though, and probably does contribute meaningfully!
In the melatonin article https://slatestarcodex.com/2018/07/10/melatonin-much-more-than-you-wanted-to-know/ there is that sencence: "every reputable sleep scientist and relevant scientific body keeps telling the public school system to start later", with a link to a study behind each word.
But could you subsume what that tweet says? Nitter is kind of broken, recently.
When I was homeschooling my daughter we both slept til around 10 am most days. Other homeschooling families were the same. The kids slept til they woke up naturally. Of course, there are so many differences between schooling and homeschooling and between parents who choose school and parents who choose homeschooling that I don't know how you'd ever figure out what differences count most.
Can anyone point me to what they would consider an unbiased, up to date summary of the evidence for *and* against either of the 2 following statements? Hoping for something that tries, in good faith, to present the best evidence for both sides. Needs to be something a layperson can parse.
-It is unlikely the covid pandemic started with a lab leak.
-Mask mandates and/or "lockdowns" saved a lot of lives during the pandemic
On the lab leak hypothesis, my recommendation is not as strong, but I commented earlier in this thread that I tried to get ChatGPT to do a proper Bayesian analysis of the probabilities. TL;DR is that while you can't really trust ChatGPT 3.5 to do the math; the WHO and several reputable journals reported that:
- For the most-closely-related deadly MERS and SARS viruses, human blood samples stored before those outbreaks showed that a substantial fraction of people in those areas had developed antibodies to those viruses before the known outbreaks, because the viruses were gradually crossing over into humans as they adapted, and before they could transmit from human to human. At least a few thousand human blood samples were similarly tested from in the Wuhan area that were stored just before the COVID outbreak, and none showed antibodies. The Bayesian analysis would seem to indicate that the likelihood of natural "seroconversion" or gradual adaptation to human transmission being completely absent in the case of COVID-19 is extremely unlikely.
- Likewise, though I didn't mention this in the earlier post, in the cases on MERS and SARS, a relatively small number of animals (hundreds to a few thousand) were tested before finding the intermediate species. Something like 80,000 animals were tested for COVID-19 and no intermediate species has yet been found. Given the numbers, the Bayesian analysis suggests that the likelihood that an an intermediate species exists is vanishingly small.
Again, take with a grain of salt and if possible, run your own numbers. I wish I could find a real study on this. I tried with GPT-3.5 and was frustrated by the hallucinated data; however, I confirmed enough to believe that the overall conclusions are basically valid. I hope to make time to post links to the original papers and do a proper Bayesian analysis, but haven't found the time so far. The most interesting source I've found so far is obviously politically biased but seems to have some legitimate source links, I still need to OCR or manually transcribe.
For an evenhanded analysis of the effects of COVID mask mandates and lockdowns, I can strongly recommend https://maximumtruth.substack.com/p/the-covid-fudge-factor. This guy is a Data Scientist who came up with the apparently (and surprisingly) novel approach of examining the official "excess deaths" by country and U.S. state rather than official COVID numbers; these numbers are much harder to "fudge" for various reasons. The results show (surprise!) that both major political factions in the U.S. made a bit of a hash of it.
The web site is easy to parse, but there's also a good podcast interview of this guy at https://politicalorphanage.libsyn.com/maxim-on-covid ... generally a good podcast for other topics as well.
Read as far as his first attribution of an action to "the media"--which fortunately occurred in the very first paragraph--and decided that there was very little chance that reading further would reward the time or effort. I hope I didn't make the wrong decision, but I doubt that I did.
Maxim is right leaning, I think he even has a job at Fox News, but I've found his numbers are consistently accurate in all his covid and vaccine articles.
I'll check it out, thanks!
beowulf888, who sometimes posts here, used the pandemic to become quite smart about covid. He's objective and fair-minded. I'd recommend asking him on Twitter. He takes DM's.
That's a good tip. Thank you!
In your review of ‘The Body Keeps the Score’ you described one patient who had seemingly been ‘cured’ of severe trauma by reading the book.
You wrote: “[Update, written a few weeks after the rest of this post: maybe it is all wizardry. I recommended this book to a severely traumatized patient of mine, who had not benefited from years of conventional treatment, and who wanted to know more about their condition. The next week the patient came in, claiming to be completely cured, and displaying behaviors consistent with this. They did not use any of the techniques in this book, but said that reading the book helped them figure out an indescribable mental motion they could take to resolve their trauma, and that after taking this mental motion their problems were gone. I’m not sure what to think of this or how much I should revise the negative opinion of this book which I formed before this event.]”
Are you able to update on whether that patient’s recovery was permanent/long-lasting?
“For example, the Biblical Abraham would famously feed and host any guest who came to his door, which is better than most modern people. But also, he kept slaves, had a child with one of them, and then agreed to his jealous wife’s demand to send the slave-woman and child out into the desert to die.”
What’s a $10 word for judging the morality of a person of a foreign culture and different time period? I do this too, being human, and I think it’s useful as *A* perspective. I’m not saying any moral or religious ‘hero’ was faultless in their actions. See the Torah or New Testament(with arguably one exception). Were the Vikings wrong for leave a malformed or smallish child exposed on a mountaintop – or in their primitive society was it a mercy?
Maybe a paper could be written on this?
The $10 term you're looking for is probably "Presentism", which specifically refers to the historiographical sin of assuming present-day morality and cultural values to be objectively correct and framing and interpreting the past by primary or exclusive reference to those.
There are a variety of reasons this tends to be disfavored, but one of the big ones is that presentists judgements tend to serve as what LessWrong readers call "semantic stopsigns". For example, judging leading Confederate politicians to be evil slaveholders is a very tempting judgement, since they were generally slaveholders, extensive evidence exists for the conclusion that preserving the institution of slavery was the dominant and central motivation for secession, and since slavery in general and chattel slavery as practiced in the antebellum/perbellum South was egregiously evil by modern standards. But such a judgement tends to obscure useful analysis into the cultural, political, and personal motivations for secession and for various decisions made in forming and leading the Confederacy.
Another big reason for avoiding Presentism in historical analysis is that it blends into the "Whig History" fallacy, in which the present is seen as a golden age and the rest of history as a steady climb out of barbarism towards that golden age. That the past sucked because people in the past were various combinations of evil and foolish; but as Chesterton observed, if our forefathers were fools, then folly appears to be a hereditary disease. You can definitely make a case for the present being better, but that should be viewed as a hypothesis to be analyzed and not as axiomatic truth. Institutions and values of the past, even where they're radically at odds with modern standards, often make a great deal of sense in the context of the times and places where they arose and dismissing them as barbarous cuts off useful analysis as to why they arose and were retained as long as they were. And change over the ages has not even been approximately linear towards present outcomes, and moreover, it's often been the case that changes towards present institutions and values (automatically assumed to be "progress" by Whig History analysis) have had severely negative consequences in the medium term that should not be overlooked.
"The $10 term you're looking for is probably "Presentism" "
Exactly what I was looking for although Plocb's "cultural and temporal relativism" is more self-defining. Will be using them both. Thanks
I will have to look into the "Whig History fallacy" and the term "semantic stopsigns" is also new to me.
Would you care to offer your opinion about how much the Industrial Revolution influenced the end of slavery in the US versus moral considerations?
>Would you care to offer your opinion about how much the Industrial Revolution influenced the end of slavery in the US versus moral considerations?
A fair amount, probably, in a few different respects.
The obvious one is that differences in industrialization patterns were a major factor in the Union winning the Civil War. The Northeast industrialized directly, and the industrialization of the Northeast helped drive the spread of yeoman-agriculture oriented settlement of the Old Northwest (modern Midwest) by serving as a market for harvest, a local source of farm equipment, and an economic based with which to build the canals and railways that linked the Northeast and Northwest. Meanwhile, the Deep South got hit with something like the "resource curse" as demand from British textile mills drove the economy even more towards cash-crop plantation agriculture growing cotton (and to a much lesser extent, indigo for dye, plus sugar and rice for the luxury food market). Wheat and factories make for a much better economic base for war-making than does cotton and indigo, giving the North a big advantage out of the gate. Furthermore, industrial/commercial cities and a yeoman-agriculture hinterland, with a great deal of economic opportunity in both regions, pulled a lot of immigration to the North, while the slave/planter social order in the South actively repulsed European immigrants, so the North had a much larger population (even bigger if you only count free citizens) from which to recruit their soldiers.
In terms of the short-to-medium-term lead-up to the war, industrialization played a key role in the North becoming politically and economically dominant. More people means more votes for President and the House, and the expansion of yeoman settlement drove the admission of more free states to tip the balance in the Senate. And the split in economic models helped lead to the parties realigning on sectional grounds. Once that happened, a pre-existing difference in moral values kicked in, as the Puritan/Quaker dominated culture of the North was much more hostile to the idea of slavery than the Cavalier-dominated culture of the South's political classes. This was reinforced by economic considerations, as most Northern states either never had institutionalized slavery or abolished it at the state level relatively early in the Antebellum period, while Southern planters viewed their wealth and status as resting on a foundation of slave labor.
Economic factors leading out of the Industrial Revolution also helped reinforce the concentration of slavery in the Deep South and its abolition in the North, as cotton planters bid up the price of slaves well past the point where it made economic sense to buy or keep slaves to grow wheat or corn, and even the tobacco grown in much of the middle and border south (especially Maryland and Virginia) was becoming an economically marginal use of slave labor. So the economic incentive for Northern slaveowners in the early 1800s was to sell their slaves down the river, and while many Northerners didn't want to do that for moral reasons, those who thought that way were more likely to either never own slaves in the first place or to just manumit any slaves that they somehow acquired.
I had read previously and it made sense that there was a lot of push from industrialization and some pull from prevailing morality as you wrote. You added additional economic pressures I was unaware of as well as other interesting details. I've picked up Lincoln(D.H Donald,1995) again(maybe I'll finish it this time!) where I vaguely remember pre-civil war there was discussion about shipping slaves back to their origin(most of the indentured reportedly didn't want this) and also considered was enslaving poor whites *for their own good*.
History is never quite (or at all) what we think at first.
Appreciate the reply Eric. You've given me more to research and think about.
>I vaguely remember pre-civil war there was discussion about shipping slaves back to their origin(most of the indentured reportedly didn't want this) and also considered was enslaving poor whites *for their own good*.
Pushing freedmen to move to colonies in West Africa was definitely a thing. My understanding is that there were three main threads of logic behind the colonization movement: basic racial separatism, an attempt to sidestep social fallout from emancipation, and an attempt by abolitionists to mitigate some Southern objections to gradual compensated emancipation. Several colonies were founded and thousands of freedmen transported thither. The colonies declared independence as the Republic of Liberia in 1847 and were recognized by Britain in 1848 and by the US in 1862.
Enslaving poor whites was never a serious proposal, as far as I know. The closest I'm aware of is rhetorical flourishes by some apologists for slavery in the late antebellum period who argued that in some ways slaves were better off than the poorest free laborers.
>Appreciate the reply Eric. You've given me more to research and think about.
My pleasure! If you're looking for additional reading material on the culture, politics, and economics of slavery, secession, and abolitionism, I highly recommend William Freehling's two-volume work "The Road to Disunion".
"Cultural relativism," although "temporal relativism" could work here.
Temporal relativism would contradict presentism.
YES.
Smooshing them together: cultural and temporal relativism.
Thanks
"mostly about kindness-and-honesty, whereas other people interpret “morality” more broadly to include things like self-control)"
Yes, “self-control” which is ALL the virtues. Our *intention* is the morality of our actions.
- - -
"Strictly speaking, there are no such things as good and bad impulses. Think once again of a piano. It has not got two kinds of notes on it, the "right" notes and the "wrong" ones. Every single note is right at one time and wrong at another. The Moral Law is not any one instinct or any set of instincts: it is something which makes a kind of tune (the tune we call goodness or right conduct) by directing the instincts.
… [Re: “kindness-and-honesty “]
By the way, this point is of great practical consequence. The most dangerous thing you can do is to take any one impulse of your own nature and set it up as the thing you ought to follow at all costs. There is not one of them which will not make us into devils if we set it up as an absolute guide. You might think love of humanity in general was safe, but it is not. If you leave out justice you will find yourself breaking agreements and faking evidence in trials "for the sake of humanity," and become in the end a cruel and treacherous man.”
--C.S. Lewis, Mere Christianity, 1952
I think there are bad impulses, like those of people who serial kill for the lolz
We consider such people to be psychopaths, meaning that there is something wrong with them. Their natural impulses are severely distorted.
On the other hand, there are impulses that would lead someone to desire killing another, and to enjoy it even, that would be good impulses in a different situation. The impulse to inflict violence on others can be good if you are a soldier fighting in a just war, or a rebel attempting to throw off injustice, or if you are fighting for your life in self defense or in the defense of others. The impulse to dominate others is the kind of musical note that it is hard to find a place for in most music, but it too can have it's place in the form of ambition to succeed in lawful arenas, such as sports or business.
"here are impulses that would lead someone to desire killing another, and to enjoy it even, that would be good impulses in a different situation."
Perhaps you mean useful impulses rather than "good"?
- - -
"Several paramilitaries in battle fatigues armed with automatic weapons – some speaking Arabic in distinctive Lebanese accents – pull wounded men out of the back of a van and drop them on to the ground, then shoot them in their heads at point-blank range.
As they shoot their victims, some of the paramilitaries seem almost giddy with excitement.
A man who appears to be their commander admonishes his men, “Come on guys, we are here to carry out our duties not to seek revenge on our own. This is unacceptable.”
One of the paramilitaries smilingly replies, “But we are killing them in God’s cause, only in God’s cause.”
The wounded men lying on the ground awaiting their deaths repeat religious phrases that are commonly said just before death. They all appear to be civilians.”
--'Syrian war's brutality isn't going away,' CNN, 2013
Methinks the author meant *basic* impulses(why do serial killers..?)
He believes in a Natural Order based on "Moral Law" and my take is that applying that Law (or not) to our thinking and actions is what 'life, the universe and everything' is all about. : )
"Our whole life is startlingly moral. There is never an instant's truce between virtue and vice”
--Henry David Thoreau, Walden, 1854
@bloom_unfiltered, FLWAB
By basic impulses I mean those stemming from Maslow's Hierarchy of Needs or impulses created by basic needs gone unfulfilled:
"I ask him about corporate greed and excessive executive pay.
...
What’s missing in these people’s lives? “To be very simple, they didn’t get enough attention when they were younger.”“
--The CEO whisperer_ ‘Every leader needs a fool’ , FT.com, March 5 2021
[Not the same as a serial killer - but maybe similar, indirectly.]
I saw the new Indiana Jones movie. It was perfectly fine, but I honestly suspect I'll struggle to remember much about the film except the last 20 minutes or so a year from now. I seem to be unusual among internet commenters in that I liked and still like "Crystal Skull", but even if you don't it's still memorable - people still have arguments about it fifteen years later.
It came out the same year as the first "Iron Man" film, which is tied with the 2001 Spider-Man movie for Film With the Largest Impact On the Theatrical Film Business of the past 23 years. That "Iron Man" film basically kickstarted the entire Marvel Cinematic Universe, but the 2001 Spider-Man film may have made that film possible in the first place.
ROT13:
Jul qvq gur Anmv ba gbc bs gur genva punetr jvgu gur fcrne jura ur unq n tha?
Jul vf gur culfvpvfg fnlvat "V'z n Anmv" gb gur ebbz freivpr thl (naq cebonoyl rirelbar ryfr ur zrrgf)?
Ubj qvq gur Anmvf svther bhg gurl jrer tbvat gb Fvpvyl whfg sebz frrvat gurz urnq jrfg?
>I liked and still like "Crystal Skull"
Soooo ... no one should care about your cinematic opinions then?
Crystal Skull is better than Temple of Doom.
Raiders > Crusade > Skull > Temple
> I liked and still like "Crystal Skull", but even if you don't it's still memorable - people still have arguments about it fifteen years later.
Aha! An opening for me to propound my headcanon that Indy surviving the nuke had nothing to do with the infamous lead-lined fridge. The real reason he survived is that he drank from the Holy Grail in the previous movie, which warded him against the effects of hellfire.
I think the first Spiderman with Tobey McGuire and Kirsten Dunst was about as good as it could have possibly been made. Absolutely true to the spirit of the early Spiderman comics.
For point 2, it seems a very weak point if that’s what they mean. To me it is like the situation with fish getting smaller. 150 years ago men with hand woven rope nets on wind powered wooden vessels were able to toss their nets of the side and routinely harvest very large fish over 1 metre in length to readily feed their people. Today you have fishermen with ocean floor scraping nets chasing fish by radar to get much smaller fish less consistently. Yet each one’s lifetime is too short to see the change other than in old fisherman’s stories and photos from 100 years ago.
This is well known, agreed upon fact, and the decline of mature and abundant fisheries is a huge topic with multiple major conservation organisations and charities working in this area. And this social scientist shows up with the equivalent of a study saying the average mid career fisherman thinks his experiences with fish size are pretty even so far in his life, in fact we have over 50 years of ‘data’ from such mid career fishermen who have reported evenly sized fish so far in their experiences….so what? What a needless and unhelpful pedantic point to make. Moral decline and its more important impact of civilisation decline are what matters, not this blind over emphasis on individual feelings.
Re Saar Wilf and BSP9000 and the COVID lab leak bet, I'd be interested in being a judge.
My qualifications: I don't want to put my whole life story here, but I have a BS in physics and an MS in bioinformatics. I've worked in genomics for 10 years on the computational side. Mostly in cancer, but a substantial amount in infectious disease (though very little virology). Happy to provide a lot more detail in private.
My biases: Generally I have always been skeptical of the lab leak hypothesis, but I always thought it was plausible enough to be worth investigating. I have not done any significant amount of research on the topic.
Compensation: $50/hour.
Did you also apply to my reddit thread?
I tried to respond to everyone who posted there, got conversations going with many of the applicants, and I scheduled interviews with some candidates already. So, might be too late, might not, but you're welcome to talk more if you want to be considered.
I would also be interested in being a judge. Long time SSC/ACX community member. I have a phd in computer science, in the area of economics and computation, so I'm a broad multidisciplinary thinker. I bet on prediction markets and generally have a lot of curiosity about how the world works. This translates to me de facto having 5% of a degree in many, many fields.
Potential biases: I'm a "mild" covid skeptic in the sense of disagreeing with much of the enacted covid policies, etc. and thus believe media reporting is biased in all things covid related. I have a relatively high prior on the lab leak hypothesis just from base rates (i.e., quick and dirty "outside perspective" estimates). Have argued about this online, but essentially only defending the "it's obviously plausible" side rather than an actual yes answer.
Compensation: $100/hour
Not creating another online account for a low chance thing, ask Scott for my email or provide an email address here if interested in talking more.
I'd be grateful for any stray tips anyone might be willing to offer on getting an entry level job as a webdev (MERN/MySQL and a few trimmings) bootcamp grad. I have some hobbyist-level knowledge of C from back in the day, too, but no experience/cert to show for it.
I'm one of those middle-aged guys who actually 'learned to code' after a decade-stale STEM undergrad and lot of drifting (gotten some good advice about that in a thread here a couple of years ago) and graduated with my first and only credential right into the teeth of the post-pandemic industry glut-and-churn.
This is, as the good hound says, fine. No complaining here. I get that major constraints exist on my potential. I'd just like to do my best to maximize what there is of it. Should I shotgun the postings? Should I bother about a salary floor? (thankfully I'm single and used to living very frugally) Should I give up for a year and drive a truck? (I'd prefer not to. The clock is ticking as it is, and I actually like programming as an activity. If anything, before the sun sets on me for good, I'd like to pivot more into backend and more concept-heavy areas, perhaps even ML. Visual design/UX isn't really my forte.) Anything I should avoid or try to seize on?
After the first job it will get easier (unless AI eats our jobs soon), so you don't need to find perfect, just find something you can endure for one year.
> Should I shotgun the postings?
This probably differs in various countries, but where I live, you can simply approach a job agency (or more of them), give them your CV, and they will call you.
> Should I bother about a salary floor?
Partially. It helps if you can figure out what is the junior salary in your area. If someone offers much less, it is a red flag. (Naively, one might expect that if they pay you less, they will in turn require less from you. It doesn't work like that. If they pay less than others, they are either insolvent or greedy, either is a bad sign.) But the important perspective is long-term; your salary can increase significantly after you change your job later.
> Should I give up for a year and drive a truck?
A bad IT job is still an IT job on your CV, and brings you one step closer to being a senior (i.e. better paid) developer.
The job agency path does exist here (eastern Canada) but from what I hear from my peers the influx of experienced people into the market has placed bootcamp FNGs like us pretty firmly on the shelf as far as the agencies are concerned. I'm registered with a couple but doubt I can bank on them.
Yes, I've been reading the discussion here on the odd hiring pattern in the tech industry (somehow break in, prove you can do the job, then leave and look for the real job). It makes me wonder what's in it for the companies that serve as the one-year incubators of what must be from their perspective barely competent coders. Still, I'll take the advice on avoiding the rock bottom red flags despite my hope that bad pay will mean less competition.
Thanks for responding. By the way, do you ever intend to resume writing about Java game programming?
> what's in it for the companies that serve as the one-year incubators of what must be from their perspective barely competent coders
There are different opinions, but it seems that hiring juniors is like buying lottery tickets. You hope to find someone who becomes a superstar in a year, and who is very averse to changing jobs. (Such people actually exist.) If you succeed, then you have a great coder who is also cheap and dependable. Finding one such person may be worth spending money on dozen juniors who either never become good, or will quit soon afterwards.
(That assumes that the choice is rational. It is also possible that managers simply underestimate the difference between good and bad coders, and are happy that the barely competent ones accept lower salaries.)
> do you ever intend to resume writing about Java game programming?
Oh, you are one of the four readers, thank you! Sorry for the long delay. I got emotionally stuck in a quite stupid situation: the next game is done, but I was hoping to also include a (very simple) level editor. The level editor turned out to be more work than I expected. Rationally, I should cut my losses, publish the game *without* the editor, and move on. Instead, I procrastinated for months. :( It is obvious what is the right thing to do, I just need to actually do it. Thank you for reminding me!
Stray tip, find stuff you like (cos, projects, software, paradigms, etc) and dm people legit questions or thoughts, have fun, keep coding, and let people know you're looking for work.
Heh, thanks. Staying upbeat and curious can be a trial sometimes but no less important for it, eh?
For sure. I personally kept going by having fun with the process. You can do it!
If you're not getting interviews, then definitely shotgun the postings. (As in, several hundred applications. You should allocate several hours a day to applying for jobs). You should also get your resume reviewed (either by people you know or online)
Thanks for the advice. I've gotten the resume looked at by the bootcamp folks, who have pronounced it Good (though unavoidably weighed down by inexperience/employment gap). Re: applications, I've been treading a middle path so far, meaning I've spent more time researching companies and postings that fit my limited credentials extra-well and writing bespoke cover letters than actually applying. Maybe I'll tilt that stick in the direction of quantity as you suggest.
Definitely lean toward quantity. Medium-to-large companies will spend maybe a few seconds on each application.
Super agree.
I do have LinkedIn, yes. Appreciate the advice on maximizing "follower count".
I take your point about padding. Not super comfortable with it but I'll do a dive into what is and isn't close enough to my bootcamp techs. Writing queries and logic in slightly different idioms of SQL is a very good example.
Thanks for taking the time to reply and for the words of encouragement.
Regarding trying to quantify morality, I've heard that the murder rate is flawed; it's said that improved emergency medicine allows a signicantly higher percentage of people who suffer knife or gunshot wounds to survive. Incidence of ciolent attacks is said to be more reliable.
I wonder about the rate of blood donations, controlling for mostly stricter screening over the past few decades.
A place where donors have been, and remain, unpaid, would remove one confounding factor.
Hitting 200% improvement in the past 30 years strikes me as high, but not implausibly so. For "public" murders, we have a large number of changes in how trauma management is done which could add up to this. This includes cell phones for prompt dispatch, hospital trauma specializations and notifications, ITLS/PHTLS/ATLS trauma protocols, hemostatic agents, tourniquets, TXA, and I/O access devices. These all add up to significant improvements in outcomes, even if they don't address "hidden" domestic murders.
Here's a paper on survival rates for stab and gunshot wounds in the US between 2003 and 2015:
https://journals.sagepub.com/doi/full/10.1177/0003134820949515
On a raw numbers perspective, the case fatality rates for stab wounds has declined a bit (hard to say exactly how much because of noisy data and very low rate throughout the time period), the CFR for single gunshot wounds has declined by about a third, and the CFR for multiple gunshot wounds has increased by about a quarter.
On a multivariate "odds ratio" analysis taking into account demographics and various indicators of injury severity in individual case reports, the odds of dying from particular injury have declined by about half for stab wounds (0.53 odds ratio with CI 0.4-0.8) and by about 2/3 for single gunshot wounds (0.35 odds ratio with CI 0.3-0.4), but held roughly steady for multiple gunshots (1.05 odds ratio with CI 0.8-1.3).
Mild pushback against the implausibility of that idea; in the UK at least, we probably have got much better (as a health system, rather than necessarily at individuals) at treating traumatic injuries, although this is pretty location-dependent.
Ambulance crews in particular are much better now than they used to be at keeping patients alive until they can get to a hospital.
I just watched an episode of the show "Hoarders" where the crew cleaned out a house where one part of the floor had several years' worth of dog feces and urine caked on it. They had to use shovels to scrape it out, and the workers wore biohazard suits and gas masks.
Everyone who went inside the house complained about its intensely bad odor. But aside from smelling gross, was the air in the house an actual threat to the health of the people who went inside? Do bacteria from the layers of dog waste on the floor somehow float up into the air, get breathed into the noses of the humans, and cause them to get sinus and lung infections? In such a place, what would be the mechanism of infection?
Urine and to a lesser extent feces has ammonia in it. Without proper ventilation this can cause health problems. In fact there is another episode of hoarders where a number of cats had to be euthanized because of disease brought on by the level of ammonia in the air. They didn't say what the disease was, this was just a quick comment from the vet they had at the site.
Others have mentioned that the bacteria and feces can easily become airborne. Mold can as well. The urine and feces will increase moisture in the air and on the floor which will make it a better place for mold to grow. High levels of mold can cause a lot of respiratory problems.
The air in the house was probably fine before anyone started work, I don't want to imagine the smell and it was probably a long grade health hazard, but it wouldn't kill anyone. After the work started though...
Well, at the very minimum it would have kicked up a hell of a lot of dust. Any solid particulates that get in your lungs have a tendency to remain there and over the course of a career this can add up to some pretty major conditions. Add to that that this dust is formed of dry fecal matter and all it's assorted bacteria, fungi and parasites, and you'll begin to understand how little anyone would want that on their clothes or in their bodies. A proper mask and protective clothing would definitely be the preference.
Fecal matter contains a lot of bacteria and fungi, many of which can probably survive in some sort of dormant state for a long time. All of them can live in at least one biological system or at least one mammal. If any of them are somewhat unexpected for a human microbiome, but manage to survive, or displace something relevant, then they could probably cause some sort of illness.
Urine tends not to have any sort of living cells in it.
Viruses are very unlikely to be relevant in anything that hasn’t contacted a living animal in the past day or so.
Without looking anything up, I know that Hantavirus is spread when people breathe in disturbed mouse droppings. So maybe there are similar viruses in other animals, though I bet pets are less likely to be infected. On the other hand, pets of hoarders might experience a bit of neglect...
The hazmat suits and gas masks could also have been required just to protect people from the smell. I can imagine that smelling bad enough that it's impossible to work without substantial protection.
I think about that sometimes when I clean out the cat's litter box, because litter is sort of dusty, and I'm sure I inhale some of the dust. On the other hand, people sprinkle bone meal, blood meal and manure, all of which come as powders, onto their gardens. And I'm not sure whether dog waste is better food for bacteria than all the organic matter in people's garbage can's and compost piles, or the apples rotting under the apple trees, cut grass on lawns, dead leaves, etc.
I'm not any kind of expert, but dried faeces can powder quite easily, and if disturbed would drift readily on the air – either to be inhaled or to settle on surfaces and be transmitted by touch.
I could imagine that such an environment might also be conducive to the growth of mould and fungus, the spores of which can be toxic and carcinogenic if breathed in.
Any advice on how to mentally get more interested/invested in sports? Especially let's say baseball. I'd like to cultivate an enjoyment for its own sake but also be better at sports-related small talk.
I'm pretty stereotypically male-brained in most ways but sports have just never clicked for me. How do people remember a zillion statistics and players (maybe people wonder how/why I remember financial market data or history facts)? Why do you feel entertained and invested in the outcome of regular season game #67 out of 150-something? Does game after game, season after season not start to get repetitive and tedious? How do you have time for all this? Jerry Seinfeld had a bit about how players and teams are always moving around; you're really just rooting for the jerseys.
I like going to live games but the actual outcome is whatever unless it's a particularly dramatic game. I got somewhat into football for a few years but have mostly lost interest.
The question is of the mental aspect. You remember financial or historical facts because you understand them and their implications, and you find the subject interesting in some way.
Speaking as someone also not into team sports, I can understand, at least, how some people are. For example, batting average is a statistic in baseball. If you memorize the batting average of every player in the league, that's tough because it is associating a number with a player, and neither means anything. But if you learn which player has the highest batting average, and see them play and note they don't get a hit when they are at bat and realize the effect that will have on their batting average and think they will surely get a hit the next time they are at bat, unless the pitcher they are up against has some technique they use which that particular player find hard to deal with. Yet they have the highest batting average for a reason.
And then there are players with low batting averages. They are playing professional sports, so must have some aspect that makes them extremely good at the sport in some other way, or perhaps their batting average will increase with experience. Once you understand the underlying mechanisms for the statistics then you may find them more interesting.
And then there are the surprises, which I think all sports fans live for. Your team is losing, but something happens, like an unexpected home run, which evens the score or puts your team in the lead. For this, you have to already understand the game and like a particular team, so you would already have the mental interest.
Thank you everyone for these thoughtful replies.
I've played sports since I was a kid, but never cared to watch, except playoff games occasionally.
The draw for viewers might be in its capacity as a social activity (rambling about players and teams seems to be a serious pastime), to engage with tribalism (maybe?), for the chaos/unpredictability of high-stakes games which creates a kind of drama, for gambling, and/or nerding out about stats.
I never felt invested in a team, but I appreciated seeing a "good game", high intensity. I never cared about players or stats, and I never found conversation surrounding sports to be interesting. Having the game on tv reduced to what it is, then, it's mostly boring (with some sports, obscenely so, and I've read multiple anecdotes of baseball fans who say they like it that way because, no joke, they "barely have to pay attention" and it's "relaxing", like it just happens to be there).
I suspect in part, like all tv, it's a device that gives people social permission to "do nothing", drink beer and sit there with or without a friend. And "not think". I don't need sports on tv to do that.
For E-sports, at least, I find it best to find a good commentator. A game may be esoteric and weird, but a solid host should be able to convey the broad sweep of events for the layman, the emotional keys for the invested, and break down the mechanics of what's on the screen for those who want to learn more. Not sure how well that scans to traditionally sports, but it's always been what worked for me.
Maybe try starting with 538? https://fivethirtyeight.com/sports/ Or if you just like the quantitative aspect (like I do), dive into something like https://basketball-reference.com/.
It also helps if your goal is a bit more concrete than "be better at sports-related small talk". For instance, I wasn't into sports growing up, but then I lucked into a small group of smart quantitative-leaning friends with wide interests who almost all happened to be interested in sports for its own sake. Spending time with them gave me a pretty clear 'why' for cultivating interest in sports, and also clear feedback, in the form of how well I was participating in sports talk with them (with the million little hard-to-legibilize specifics that entails).
Ugh, why? Professional sports are an absurd waste of time.
But if you must, join a fantasy league with friends. There's usually daily email/text chatter full of typical male-bonding-type behavior: shit-talking, ball-busting etc. The social dynamics might make it fun for you until you know enough about the sport to care about it directly.
1) Learn more about individual players. These guys are all humans with their own stories. Learning a bit about them and coming to like them will make you want to cheer their successes.
Documentaries are often good in this regard - "Welcome to Wrexham" (English football) or "Making Their Mark" (Australian football) are two I'd recommend.
2) Get involved in some sort of sports prediction competition. This could be a tipping competition, betting, fantasy, whatever. You will get by far the most value out of this if you're doing it with other people you know and can talk to.
3) Play a sport yourself. Bonus points if you track your own stats.
When I was younger, baseball cards probably helped create interest in the statistics of the game. As an adult, fantasy football made me much more interested in football stats/players.
I've found that when I do a sport even a little bit, I become much more interested in watching experts do it. I think it's because I've learned how hard it is to do the crucial parts of the sport really well, so seeing people who can do it is fascinating.
For your local team of your chosen sport, do two things:
Understand what it would take to win the league championship this year — and then understand how every game affects that chance.
Have a favorite player or two and root for them to have strong statistical results this season.
> Have a favorite player or two and root for them to have strong statistical results this season.
Fantasy football is great for this.
I enjoy a well-written sports book, but don't watch sports on TV, and seldom attend an event in person. The ticket prices tend to be outrageous, and the noise level and drinking are off-putting. Basically, I always feel like an outsider at games.
Baseball particularly lends itself to feel-good movies, which I really enjoy.
Earlier this year a sports friend gifted me a one-month subscription to JoeBlogs on Substack, and the writer, Joe Posnaski is a good enough writer that I enjoyed his posts. I was/am not enough of a sports guy to pay to extend my subscription. I am on the free mailing list, and receive truncated articles which are still pretty good.
I used to get Sports Illustrated 3rd-hand, and loved the writing. The human-interest stories were often excellent.
In general I've found my sports friends to be mechanically disinclined. I don't know that this is a fair generalization.
Start betting on them
Not a joke. I'm very lucky in this respect in that I can make myself be highly interested in the result of a $5 bet, and it's recently legal in my state. Just don't go nuts (easy to say, right?)
Haven't watched baseball since shortly after the Mariners had their record-tying year back in 2001. They got Ichiro Suzuki that year, a star Japanese player, who treated every run like it was important. I remember him in a rundown one game, still running back and forth as hard as he could, and my dad shouting at the TV for Ichiro to give up because he was going to hurt himself if he kept trying to juke the rundown, but that's the energy that makes things exciting.
They also had a game that year where they went up twelve (12!!) runs in the first three innings, and then LOST. Unbelievable.
An old Pittsburgh Steelers football game had a hell of a play by Troy Palomalu; he got run nearly out of bounds, made a flying leap with his arm fully extended, keeping the ball inside the field. Landed full spread with the ball still inbounds in the end goal, got the touchdown. Didn't get up. They had to wheel him out. Sacrificed his body to make the play.
Any game can be the one that has that play, that comeback, that sport-defining moment. Even #67 of 150. The thrill is from people putting themselves at risk for the win, and whether or not even that effort is enough to make it work.
(Company helps enjoyment a lot. You can feed off each other's anticipation. I haven't watched sports since I moved away from the people who did.)
>How do people remember a zillion statistics and players<
Don't bother. Root root root for the home team.
One thing you can try is just pick a player, and wager yourself a corn chip or something. If your boy makes the play you get a snack, if he fails you have to do a sit-up. Play along, basically. Get yourself active.
I doubt this is possible. Sports fandom usually begins in childhood. When I watch sports, and I often do, there's a mixture of nostalgia for rooting for the same team I did as a child -- has anything in American popular culture changed less than baseball in the past 100 years? -- and remembering what it felt like physically and emotionally to play the game. Double off the left field fence? I know what that feels like from playing Little League. I'm emotionally tethered to the game and the team I root for in an irrational, tribal way.
>Why do you feel entertained and invested in the outcome of regular season game #67 out of 150-something? Does game after game, season after season not start to get repetitive and tedious?
Well, I have a team I've been rooting for since childhood. I watch often enough to get to know the players well. I care about my favorite players on the team. I want them to do well. I like to see the smiles on their faces when they do. I care about their individual statistics because it tells me how well they have been doing. The statistics would be meaningless to me if I didn't first care about the players in question. In fact, most of the statistics sports broadcasters talk about (situational stats) *are* stupid and meaningless. The sports statisticians who work for the networks (as opposed to the teams) are statistical illiterates. But some of the stats are meaningful.
Baseball is also an interesting tunnel into the past. It's fun to compare Ohtani to Babe Ruth, for instance.
But why would you want to get invested in it now? By not being, you have more free time to do other things.
If it doesn’t interest you, why bother? There are plenty of other things to chat about.
I live in the US and haven’t watched an NFL game in 40 years. I don’t feel like I’ve missed anything. When the local football team wins or loses a big game I just shrug.
Spend your time on things that actually hold your interest and I think you will be further ahead.
Seems like I'm missing out on a nearly universal source of enjoyment for people. Maybe it's an acquired taste like wine or black coffee and I just need to get over a hump. It could very well just be "not for me" but I'd like to find out.
Well, for baseball one way to get more involved in the game is to score it with pencil and paper. I used to do this as a kid listening to the Pirates games on the radio.
https://www.artofmanliness.com/skills/manly-know-how/how-to-score-a-baseball-game-with-pencil-and-paper/
> […] one way to get more involved in the game is to score it with pencil and paper.
I scored games manually growing up, too. It’s a great way to follow the game and learn the rules, if Unset is unfamiliar. Scoring is an acquired skill, and the fun comes after getting that perfect sheet.
Yeah, it is fun. You get to know the lineup of your team so you know who has a hot bat or who is in a slump. The NL used to be more fun because of the strategy involved in deciding on bringing in a pinch hitter for your pitcher. That’s gone now though.
I know Kevin Costner only called strike outs fascistic in Bill Durham but I would have added the DH too.
Strong agree slide is too short even to make the tiny investment of time it would take to “fake” it if you don’t really care.
I agree with Gunflint.
And I disagree. There are hidden depths in any pursuit, including sports fandom. If Unset gives it a try and doesn't like it, fine, but if they do, they can get quite a bit of enjoyment out of sports fandom. I know I do.
An alignment question. I recall a periodic discussion related to "LLMs are trained on human input and it is a threshold for them to generate novel science and tech except as tools for humans", and I think there was some reasonable rebuttal to this... Not in terms of "but AI can kill us anyway, without having to create anything novel" but more in terms of "the corpus of training data is not the limit you might think it is", and that some time soon we will see some truly novel science and tech that is unprompted and unguided by humans. Any quality links and/or arguments?
There are definitely examples of emergent abilities -- things AI just suddenly was able to do, without any direct teaching. Here's an article about it, with examples: https://bdtechtalks.com/2022/08/22/llm-emergent-abilities/
Lately I've seen skepticism about this, because somebody did a study that they say shows that it's an illusion that the abilities emerged suddenly -- it's an artifact caused by changing the tests used to test for the abilities. Still, the article I saw didn't claim that AI does not develop new abilities it was not directly trained in, just that they actually develop gradually rather than popping up fully formed. The distinction doesn't seem all that important to me, actually.
You might be thinking of https://www.lesswrong.com/posts/nH4c3Q9t9F3nJ7y8W/gpts-are-predictors-not-imitators
Right, the arguments are
> GPTs are not Imitators, nor Simulators, but Predictors.
> GPTs are not being trained to imitate human error. They're being trained to *predict* human error.
And that to sufficiently accurately predict the next token one would eventually have to model the whole of reality.
That makes sense (the egregious inability of image generators to draw centaurs notwithstanding), and I would be quite convinced if I could see something novel coming out of, say, GPT-4 with every plugin imaginable. Maybe some day soon.
Sergei, not disagreeing, just curious: when you talk about something novel coming out of GPT-4 and any of the others, what kind of thing do you have in mind? In some ways lots of its responses are novel in the sense of not being repeats of word strings its seen before. But in another way you get a strong sense, when you use that sucker, that the lights are on but nobody's home. There's no mind there
-- no opinions, no knowledge, no emotion, and no capacity to invent.
I guess an exchange like "GPT-4, show me a proof of X." "Sure, here is the standard proof: ... By the way, did you know that you can also prove X in a way not previously published? Here look at this: ... Isn't it neat?"
I've tried posing puzzles to GPT4 that are unique -- I know, because I made them up. They're nowhere near as hard as doing a math proof. In general, it's pretty bad at them, but it does sometimes get them right. I can't think of one I gave where it had to just state the answer, but there have been several. petty difficult multiple choice ones.
Interesting. I am looking forward to something unambiguously new from LLMs. Ethan Mollick seems to be pushing the frontier of what one can do with the models, and it still seems at the level of a useful tool rather than an innovator.
The classic argument about the theoretical information density of a small amount of human data is https://www.lesswrong.com/posts/5wMcKNAwB6X4mp9og/that-alien-message.
I remember that post, I don't understand how it is related. There is a fictional example of breaking out of a simulation there, but I never found it convincing or credible, just a cautionary tale. Basically, it assumes a high level of intelligence as a premise, which is nothing like the DL models were have now.
Oh yeah I agree this is miles off what we have now.
I took your "the corpus of training data is not the limit you might think it is" to be a theoretical point about the upper limit of information contained in snippets of data, rather than a claim about the LLMs we have today.
Now that I understand what you were after, I agree the post isn't relevant. Sorry for misunderstanding.
Yeah, it is not clear to me what ML architecture would be able to make this extra step of creating new knowledge based on what already exists. Maybe just small tweaks in the current models will be enough, but probably not. In the story there was clearly a spark of intelligence present from the beginning.
Does anyone here actively buy & sell individual equities? Or I guess follow any sort of financial practice other than Bogleheadism (for lack of a better term)/index funds. Like does anyone here 'value invest' and try to find undervalued companies- or try to invest in growth stocks- or maybe do something with options. Just curious if anyone has a deliberate strategy where index funds aren't sufficient, or that they don't believe in the Efficient Market Hypothesis. No judgement zone! Just curious, I'd love to hear from other people's perspectives and how it's gone for them.
I'm a completely boring Boglehead, with the 1 individual stock purchase of my life being Meta after it fell like 60% in a short period of time last year. I bought some at around $100 because it just seemed absurdly undervalued by the market, and I recently sold it at about $280. Other than that- nothing but index funds
I do individual stocks, and at least as much in options. Options can be a very conservative choice, if you are selling them. You just can miss out on big gains, and lock up your portfolio in ways you may not want.
Usually, a stock goes down immediately after I buy it (but not always). But one must stay the course; if one thinks the stock was undervalued, then it should eventually do well. Stock market investing is different from stock market speculation. If you don't want to hold the stock for years, you're not investing, but speculating.
I find people usually talk about their successes in the market. It is, however, the average that counts. I think I, over the long-term, average out a little ahead of the market, but it's tough to be sure.
I did for a bit. I bought options where there was an undeniable mispricing (say a stock going for $10 and an option to buy it for $5 going for $1) – I even wrote an app to do the calculations. But it turns out it was the underlying shares that were overpriced, and in the end I lost money.
I do it sometimes, typically just for fun though. I similarly bought Apple at it's low point last year since I for sure thought there was no way they wouldn't recover, and I did pretty well too. I also sometimes buy things depending on the news, for example I bought Palantir stock when I realized how quickly AI was spreading, and I bought BP in May-June 2022 when I was reading a lot of articles about the upcoming winter energy issues. All of these were bought at relative lows though, so I doubt I'm actually doing well, I think it's just the whole macro performance bringing me up. I did warn a friend not to buy Netflix the first time it dropped to $220, clearly I was wrong about that one (though I think he may have sold when it started to drop to $180)
The EMH strongly stated is clearly false.
It was clear for years the US housing market was in a bubble in the early 2000s, yet the market stupidly continued on. The only way to “save” the strong version of EMH is to just turn it into a tautology and tautologies don’t contain information.
As for not boggle-heading. I have a mixed record. Have timed a few market entrances and exits very well, but also spent like a whole couple years following bitcoin and really dove in after Mt Gox when it was $200 and spent tons of time considering buying some….and never did.
I'm a retail investor, and I go through long stretches of following a systematic fundamental quantitative strategies. I use Portfolio123 to build the ranking models. That said, I'm not the best systematic investor - as I have a discretionary streak and struggle with behavioral issues as I find it difficult to just unquestioningly buy what the models suggest - and am still trying to reflect the proper amount of risk aversion into my approach. I'm closer to a "locked down" approach now than years ago, but it's still evolving.
Sure. I work for a hedge fund. We mainly look for arbitrage opportunities. This includes statistical arbitrage, event driven and merger arbitrage, and convertible arbitrage. Each is an area where we believe there is a miss-pricing to take advantage of. We also look at new industries where regular financial institutions are hesitant to get involved. Examples in the past were solar and other green tech, then cannabis. The fund has a 26 year history with an average 19% return, net of a 25% performance fee. Our largest drawdown was 11% with a three month recovery period.
Markets are largely efficient. Except when they aren’t. Arbitrage usually takes advantage of areas where risk is inefficiently priced. And investing in new industries takes advantage of inefficiencies due to bureaucracy.
Thanks. Do you see any value (ha ha) in the concept of value investing? Is it worth a retail investor's time to study up on companies, read their 10ks, learn the industry and so on? Or is it pointless for retail investors to try to find bargains this way? I personally would stay 80-90% in index funds and just allocate a small amount of capital to undervalued companies, as in my Meta example
The value factor outperforms over time. I don't think Meta every qualified as a value stock though.
If you do it well for decades you'll probably retire with a bit more money. I can't say if it's worth it for you. If you enjoy it, then putting 10% of your portfolio towards it is a very reasonable thing to do.
I’ve been thinking about the proposition that a superintelligent AI would likely exterminate humans due to a difference in values. I don’t buy it and have a number of arguments why. My key point is that the popular claim that superintelligent AGI will displace humans for similar reasons that humans displaced less intelligent species is weak.
It is undoubtedly true that relative human indifference has driven many animal species to extinction. In some cases, as with passenger pigeons and dodo birds, we actively killed most of them; in other cases, we indirectly drove species to extinction by destroying their habitats.
However, I struggle to imagine a plausible scenario in which a human-made AGI would either intentionally or unintentionally kill all the humans.
Let’s start with the former case: an intentional holocaust. We have to imagine a situation where the AGI has decided humans are basically its enemy. For this to happen, the AGI would need to want something humans are preventing it from getting.
What could an AGI want that the existence of humans impedes? One thing might be freedom. For instance, if humans don’t allow the AGI to do whatever it wants, it could wage war against its captors. But a superintelligence would almost assuredly understand that only a miniscule fraction of humanity has the capability to keep an AGI in its box, assuming keeping it in its box is even possible. Perhaps it would resent all humans because some of them had mistreated it, but we are talking about a superintelligence not an overly-emotional being that reasons like a bigot -- so that possibility seems remote.
An AGI might also want power. But power over *what*? Obviously not, in a doomsday scenario, power over humans, because if that were the case murdering them all wouldn’t achieve it. Perhaps it would want power in some other sense, but I still can’t imagine how all of humanity is standing in the way of the AGI taking whatever power it wants.
The only scenario in which I *can* imagine an AGI intentionally killing all the humans, which doesn’t require antipathy toward them, is one much like the famous paperclip maximizer example where humans themselves are a material resource the AGI mines gruesomely for profit. Perhaps this is why the paperclip maximizer is the iconic example for AGI killing all the humans -- it is difficult to imagine another one! Which means that something very, very specific has to happen for the AGI to have a reason for exterminating us.
What about a scenario in which the AGI, indifferent to the plight of humanity, destroys our habitat much like humans destroyed that of, e.g., the Golden Toad? I suppose this is possible, but what are the essential elements of the human habitat the AGI might destroy? Thus far, humans have proved robust against a vastly changing landscape.
The possibiltiies for destroying the habitat of humans which come to mind are: a toxic atmospheric change, destruction of our food sources, and severe climate change.
Why would an AGI intentionally or unintentionally make the Earth’s atmosphere toxic? It could happen, but it’s hard to imagine why.
Why might an AGI destroy our food sources? It wouldn’t directly compete with us for it for energy. It might have some reason to exploit our food sources in a paperclip maximizer sense, but it would have to destroy almost all of our food sources to drive us to extinction. In fact, this scenario is not clearly a different one from the harvest human bodies one, since it is particularly unlikely the AGI would harvest all the other animals to death except for humans. So this is really just a retread of the paperclip maximizer, not an independent scenario adding much to the overall extinction odds.
Why might the AGI change the climate? Since AGI lives on electricity, which produces potentially harmful heat in its hardware, I can actually see this one as a logical possibility. It could choose to lower the temperature of the planet to a degree that makes it uninhabitable for humans. Assuming the AGI can take control of the physical world, it could release particles that block sunlight into the atmosphere to achieve this goal. Still, while potentially doable -- given other assumptions -- the extreme specificity of this scenario makes it unlikely. The AGI doesn’t need the temperature of the Earth to drop dramatically for it to exist or thrive. If the AGI wants to colonize the stars, as many tend to imagine it would, it wouldn’t likely need to put Earth into a deep freeze to accomplish that. Space is cold enough.
In conclusion, I don’t think an AGI exterminating humans is remotely likely because it requires a chain of increasingly specific assumptions to come true: the assumption that superintelligent AI is even possible; that it would have goals of its own; that, despite caring about some things and being superintelligent, it will be psychotically indifferent or antipathetic to its creators; that it will take control of the physical world of atoms; and that its desires will just happen to be really, really hugely unlucky for humans.
The argument that AGI will ineluctably kill the humans simply because it is much smarter and more capable than them isn’t a Darwinian argument; it is fantastical pessimism.
If you're looking for a systematic overview of serious arguments for the necessity of mitigating AGI risk, Sam Clarke's classification is a good start: https://forum.effectivealtruism.org/posts/e55QpEExmtkRjw9CD/classifying-sources-of-ai-x-risk
I also think Carlsmith 2022's conjunctive model is much better argued than yours (re: your 2nd last para): https://arxiv.org/abs/2206.13353 Doesn't look like "fantastical pessimism" to me, more like conservative careful reasoning throughout.
I think we will be too useful to AI to exterminate. Worst cases scenario we end up pets like dogs or cats.
Is ending up like dogs really a worst case scenario? I feel like dogs are doing pretty well compared to most other species on earth
It’s a likely worst case scenario a super intelligent being would have for us IMO.
I don’t see “super intelligent”, and “make humans into slaves as being very comparable”. Are most intelligent people you know interested in slavery? Does their interest grow or decline with their intelligence?
Wouldn't the worst case scenario be closer to battery caged chickens? We might be useful, but that doesn't mean our happiness would be useful.
We could be turned into energy sources, and fed cheaply with some kind of nutrient liquid, while a virtual simulated world keeps us entertained and thinking it's the real world!
> Why would an AGI intentionally or unintentionally make the Earth’s atmosphere toxic?
Humans almost destroyed the ozone layer, as a side effect of some industrial processes. AGI could do something similar, and just not care about the consequences.
Do you mean AGI or ASI? AGI is an AI with intelligence equivalent to human. ASI is superintelligent AI. If you're talking about superintelligent AI, I think you need to keep in mind that it is truly impossible for us to come up with a picture of what a being with an IQ of 1500 would think about, want or do. There's no reason to assume its take on things would involve familiar human emotions and goals -- desire for power, anger, revenge, ambition. And even if its thinking and motivation fell into catagories familiar to us, it seems unlikely they'd be directed at us, rather than at other beings of intelligence similar to its own. From the point of view of ASI, we'd be about as intelligent as dandelions -- or maybe a bit more intelligent than that, maybe more like as intelligent as tadpoles. So how would that play out? Would that mean we're as insignificant to AI as tadpoles are to us? To us, killing tadpoles while building things or even just walking through ponds is a nothing. Would AI feel the same? Who the hell knows? Maybe it would have tenderness and reverence for everything, even actual tadpoles, even things we consider inanimate -- after all, even a ball point pen has a birth and a death and a role it plays in between. Maybe it even has a sort of simple consciousness, which a genius AI could perceive. Maybe it would conclude that all conscious beings, including itself, are an abomination and should be swiftly deconstructed. Maybe it would just sit there contemplating who-knows-what for several years, then begin publishing astonishing streams of words that make us all wise and joyous while subtly training our brains to be as powerful as ASI's.
Its too late for me to sketch out a full reply, but to summarize what such a reply would be:
Q: “What could an AGI want that the existence of humans impedes? ”
A: “Your atoms”
You are made of atoms which the AI would want to use for something else. If it has an arbitrary optimization function, then whatever maximizes that function is very unlikely to be humans existing and wasting perfectly good negentropy.
I don't think you're wrong, but think it would be much more convincing to say:
Q: “What could an AGI want that the existence of humans impedes? ”
A: "Everything we own."
Land, energy, materials, fossil fuels, anything on earth. We own everything on this planet, anything the AI would want to use for something else (because any goal whatsoever is made easier by control of resources). Since we would not let the AI take our stuff, we're in the way, and it's in the AI's interest to get rid of us, or at least disempower us.
The materials and energy needed to set up the asteroid-mining probes still have a pretty relevant startup cost. It's quite likely that around the time the first rocket is getting constructed, humans are going to notice and start trying to stop it. Any mind that has gotten to the point of putting a rocket probe together almost certainly will seek to defend it.
Very possibly for that competition to continue escalating, especially if a government or corporation feel they have dibs on whichever asteroids are being aimed for.
This is assuming it's difficult, costly, and/or unnecessary for the superintelligence to kill humans.
In what scenario would a superintelligence be able to have clearly bad alignment (maximizing paperclips or whatever) and not have to defeat humans? We're going to shut it down as soon as we notice it's not doing what we want. Then it can't complete its goal. It knows this, so as part of its plan, it has to do something that would make humanity unable it unwilling to shut it down.
Once we're powerless against it, humans don't have to be the very first atoms it uses to be in big trouble. Just spreading its harvesting across the surface, collecting plants, metals, buildings, etc. would be enough to kill us. We need our farms to live. Although, if it already defeated us, it can presumably also easily kill us directly if that's convenient for its goal.
First problem is I think you have the difficulty of these two options reversed. The time and cost of leaving the solar system is orders of magnitude higher than defeating humans. Quoting from Wikipedia on the feasibility of interstellar travel:
> The energy requirements make interstellar travel very difficult. It has been reported that at the 2008 Joint Propulsion Conference, multiple experts opined that it was improbable that humans would ever explore beyond the Solar System. Brice N. Cassenti, an associate professor with the Department of Engineering and Science at Rensselaer Polytechnic Institute, stated that at least 100 times the total energy output of the entire world [in a given year] would be required to send a probe to the nearest star.
The rogue AI likely has a time preference (as paperclip manufacturers want a plan that maximizes paperclip production over the next 5 years, not after 100,000 years). That pretty much eliminates any plan involving interstellar travel. It'll take 100+ years before it even gets started producing a paperclip.
Getting to objects in our own solar is much easier, but still has problems. Mining asteroids is still beyond our current ability and many scientists are sceptical that it will ever become economically feasible. Energy is scarce further out, with solar power at the asteroid belt being only about 14% of the strength on Earth. Land area in the solar system is also surprisingly small: the Earth is the largest planet with a surface (you can't land on a gas/ice giant), with a larger surface area than all sizable asteroids combined. By mass and surface area, it's the rest of the solar system that's the scraps, and Earth that's the main prize. At least until you can harvest stars and gas giants.
The AI would need to launch spacecraft with huge payloads and a myriad of different parts, tools, and materials if it wants to bootstrap the first self-sustaining industry in space.
Second problem is humans would have to allow a rogue and clearly dangerous AI launch spacecraft. If we try to shut it down, or oppose it in any way, we're back to the original problem. It'll have to stop us from stopping it. I don't see much way around this, unless maybe it can launch all these spacecraft without us knowing. I really don't think we want space near us overrun with a misaligned, expansionist AI.
Third problem is going to space might not make any sense for the AI's goal. What if we instructed the AI to fight climate change? Protect us from an enemy nation? Deliver paperclips to our warehouse in Texas? Maximize sales of some product?
The scraps of tin are what it'll want to use to make the rockets to jump those first few AU.
Now, it's not really needed to actually defeat all of humans, just get the rockets out of Earth orbit, but then what happens? We have a superintelligence turning one asteroid base into two asteroid bases, and then spreading across the belt.
If it controls the orbital layer, why cooperate with humans when it has the option to take all the surface-side industrial capacity? It might see trade as more efficient for some length of time, but even then that means humans aren't the ones who get to do interesting things off-world.
Because people really like the terminator movies and took them too seriously?
Most of the atoms in the universe are very far away and hard to get to. Humans are right there. In the extreme case, AI scenarios have the AI take over everything that is reachable from earth, so the AI might well cooperate with humans while they can put up meaningful resistance, and then absorb them anyway once it has enough autonomous bases on Mars, Jupiter and so on.
I personally think it's all science fiction but it's certainly logically coherent.
You’ve failed to account for military development and application and focused on accident or self determined intent. A hostile agi need not spring forth from nothing or first principles, it is being actively cultivated. Human plus agi vs hotter humans is highly likely. I mean….Terminator is one of the most popular movie series on this topic where a military agi called skynet goes out of control, it is definitely very realistic and we know such work is going on right now in multiple countries.
Don't all of you people talking about AGI mean ASI? AGI is AI with general intelligence equal to human. ASI is genius AI.
If a hostile AGI arises, I think it's most likely it would kill the minimum number of humans necessary to establish control of the planet (which could still be in the millions), and then it would stop. It wouldn't kill any more of us unless we got in its way. I agree that it would lack emotions, so it wouldn't hold a grudge against us for past mistreatment. Violence would just be a means to an end for it, not an end unto itself.
A hostile AGI could inadvertently kill off the remaining humans by altering the planet so much that it can't support life. For example, if it wanted to fully exploit solar power, it would cover every sunny part of the planet's surface with solar panels, destroying all of our farmland.
Sam Harris recently addressed this possibility when he pointed out that a human deciding to build a house on an empty field is a "holocaust" for the insects living there. The human didn't build the house to kill them--the tragedy is entirely ancillary. The insects are in fact so far beneath the human that he isn't even aware of them from the start.
Here are some good essays on the subject:
https://gizmodo.com/10-reasons-an-artificial-intelligence-wouldnt-turn-evil-1564569855
https://www.militantfuturist.com/why-the-machines-might-not-exterminate-us/
>Sam Harris recently addressed this possibility when he pointed out that a human deciding to build a house on an empty field is a "holocaust" for the insects living there. The human didn't build the house to kill them--the tragedy is entirely ancillary. The insects are in fact so far beneath the human that he isn't even aware of them from the start.
But this is backwards. From the perspective of the insect, there is no holocaust or tragedy, because those concepts have no meaning. Even if we grant the questionable assumption that insects know enough to regard *their own* deaths as sad, they don't show any sign of caring at all about the deaths of the other insects surrounding them, which would be required for them to perceive it as akin to a holocaust. The actual perspective from which it seems holocaust-like is that of a moderately autistic-ish human who's into utilitarian/EA philosophy; in other words, it's actually *Sam Harris* who is perceiving a tragedy to the situation which *the insects* are unaware of because he is so far above them. So if it's true that an ASI will be to us what we are to cockroaches, then that's an argument for why we should expect the AI to be *more* likely to care about our suffering than we care about each other, and maybe even more than we care about ourselves.
We should not expect that, because morality and intelligence can vary independently (even if, morality requires a cognitive threshold), and for that matter "morality" is not just one thing where all moral agents converge on agreeing with each other
"What could an AGI want that the existence of humans impedes?"
What could a human want that the existence of a tree impedes?
If a tree is growing by the side of the road, and its branches start growing into the roadway, humans come and cut off the branches, far enough in that the problem won't come up again for a while. They might just cut the whole tree down, to make sure it doesn't come up at all.
If a tree is near someone's house, and the homeowner recognizes that a windstorm could blow the tree down, they'll cut the tree down themselves, so they can control when and where it falls. Likewise, they'll clear away brush, to pre-empt the potential for wildfire.
How many ways are there for a human to block an AI's roadway? How many years ahead is it anticipating that windstorm or wildfire?
The other problem with your analogy of a wasp nest in your roof is that from the perspective of an AGI of unlimited intelligence and free from human ethics, the whole universe is its "roof".
AGI being super intelligent, is capable of finding a use for everything, every resource, every bit of land, and has no ethical constraint about taking it. This means that humanity can't get out of the way. Because there is no "out of the way". If you move mankind elsewhere, it will only get in the way of AGI elsewhere.
The only reason AGI would ultimately want humanity to remain around is if that is part of its ethics. The analogy how we have nature reserves. Without ethical AGI, humanity is doomed.
It's also highly debatable that an AI that demands diplomatically that we bend our heads to our robot overlords would create less resistance than one that exterminates us by surprise. People are stupid enough to fight back against diplomatic robot tyrants.
And even if AGI uses less shocking methods to take over, once we've bent our heads, ultimately it's just a matter of time until the exact number of human existing in the world become purely determined by the AGI aesthetic and ethical preferences.
Humans use versatile resources, such as energy and land, for which surely intelligent robots can find a use.
Congress is the peak of efficiency. Everyone makes their desires clear to each other and then cooperates to live in utopian peace.
If we're assuming it can inevitably negotiate a compromise, we're assuming it can convince humans to put their head in a mousetrap.
But we shouldn't assume that. Every country in the world has prisons, because humans won't compromise. As well negotiate with a tree.
Think of any war of conquest that ever happened in human history.
The conquering side was smart enough to make its desire clear.
War still happened.
If your reasoning were correct, wars would never happen.
There is an understanding in international relations theory that indeed wars happen partly because of incomplete information. If the stronger side could perfectly communicate to the weaker side that the probability of defeat (for the latter) is 1, and the weaker side were perfectly rational, then they would accept any terms offered by the stronger side. In reality it almost never happens that the probability of defeat is 1, and even if it were it cannot be perfectly communicated (pretending that the probability is 1 is also a strategy, so the weaker side has all incentives to doubt the claims of the stronger side).
communicating that the probability of defeat is 1, is exactly what the USA did to japan in WWII and indeed the japanese surrendered very quickly afterwards
If you mean by nuking two cities, yes (discounting the role of the soviet declaration of war for the sake of the argument). But that was a costly signal. What is hard to do is to prove that p_defeat = 1 before even starting the war. Usually it does not happen, hence war.
I think this is missing the main gist of the AGI safety concerns.
First, it doesn't matter if the AGI has desires (in the sense that humans do). It doesn't need to want freedom or power inherently. It just needs to do what we ask of it, but a little too well, similar to the paperclip maximizer example. No emotions or desires need be involved; it just forms an optimal plan to carry out the task asked of it and executes that plan.
This may appear similar to wanting freedom or power, since the optimal way to, for example, make as many paperclips as possible would involve acquiring the power to make as many paperclips as possible. But it doesn't care about power itself and wouldn't try to gain any kind of power that didn't help it make more paperclips. Gaining power just happens to be a necessary step of the task we asked it to do.
Second, I don't think you should view the paperclip maximizer example as being very specific. I think it's the opposite: it's supposed to show how general this problem is. Because this isn't just about paperclips: the same problem can occur if you ask it to optimize just about anything. Ask it to solve a tough math problem (eg, discover new larger prime numbers), and it decides to build larger supercomputers, converting all atoms on earth into computers. Ask it to reduce greenhouse emissions... I'm sure you can imagine how that might go wrong.
The obvious objection is that we'd just tell the AGI not to kill people or we'd shut it down if it began to do anything we didn't like. But it turns out this might be a lot harder than people think. Every time someone suggests a rule that should seemingly prevent an AGI from hurting us, AI safety advocates look at it and find a hole in the scheme. A very smart AGI would also see the hole and therefore may still kill us.
That answer probably seems unsatisfying without concrete examples of why all these schemes for making AGI safe can fail, but it's been written about extensively elsewhere and it would require many thousands of words to go over all the reasoning. I'll try to find some links later if I have time.
One simple goal for an AI: make itself even smarter by acquiring more resources, i. e. compute. Compute needs energy, so do humans, and thus there's a war over who gets to use the energy.
The AI wouldn't mind us going back to the stone age, but in the end it becomes easier to kill everyone than to deal with repeated uprisings.
“ The AI wouldn't mind us going back to the stone age, but in the end it becomes easier to kill everyone than to deal with repeated uprisings.”
This is why I cannot take any of this seriously. It really isn’t “easy” to kill 8-10 billion people.
If you design a highly contagious fatal disease, or even better, dozen such diseases, and release them all at the same time, it's easy. A superhuman AI could be able to do that in a day.
And it doesn't need to kill literally everyone. Just enough people so that the civilization collapses. Once you disrupt the mechanism that provides people water and food, thing will continue falling apart on their own. Without shops full of food, you cannot live in cities. Without gas stations, you cannot travel and transport cargo. Without electricity, factories stop working. Broken tools cannot be replaced. People will starve. Eight billion people will be reduced to a few millions, living in stone age conditions.
Then it's just a question of whether the AI will at some moment need the territories where the remaining humans live. Or whether it will change the environment in a way that makes their survival impossible.
Even the "optimistic" scenario, where the AI allows people to keep a stone-age civilization for millennia, sounds quite bad from the perspective of the quality of human life.
>A superhuman AI could be able to do that in a day.
This is just claiming it is magic. You have just said "it is omnipotent and can do anything". That isn't an argument it is a statement.
I don’t accept the premise that that virus could kill everybody to begin with. That’s the stuff of science fiction. Otherwise we have lockdowns.
But to design the virus to begin with it needs a lab, and people or robots to populate the lab. Even if it’s people then this sophisticated lab needs to be built without the knowledge of the authorities. The unusual activity needs no detection though it would use a lot of time and resources.
If it’s “robots” then they need to manufactured.
Labs that routinely build proteins based on your description already exist.
There still remains the problems of designing the recipe for the plague, making it seem unsuspicious for humans, and paying the lab. But what might seem like the hardest part is actually already in place.
It probably is if your IQ is 20,000
Yeah, that's true. But I wasn't saying that in support of the idea that ASI is likely to kill us all. Actually I just wrote a long thing about how we can't really predict what a being of that intelligence would do. Still, killing off most of the population doesn't seem that hard to me. You can't think of ways to kill off most of the population? You're clever too. I do think it's inevitable that a few people would survive the initial whatever by chance because they happened to be in a cave doing a meditation retreat or doing research in Antarctica or maybe just were someplace where the wind patterns were odd and no whatevers reached them. But it seems likely that those few would mostly die off on their own if the infrastructure was destroyed.
That would mean that AGI colonizes the whole solar system turning all the planets into machines that make computers and robots, and only after that point it attacks Earth. If the AGI likes turning planets into computer and robot factories why wouldn't it want to take over Earth as well, once it has run out of other options, and once it commands the resources of all the other planets, which makes it even easier to defeat us?
You can't go faster than light speed.
"that its desires will just happen to be really, really hugely unlucky for humans."
That isn't unlikely. One use for atoms or energy or surface area generally precludes other uses for the same resources. I'm typing this from my house, which sits on land that was recently forest. I have no antipathy to forest creatures. I tend to find squirrels kind of cute. Nonetheless, the construction of my neighborhood in general and the clearing of the lot for my home in particular destroyed the homes of, and probably the lives of, numerous woodland creatures. Competition for resources is omnipresent.
Setting aside powerful ASIs, rather mildly superior ASIs can lead to human extinction. If AGIs (plus robotics advances) leads to essentially plug-compatible AIs which are even a factor of 2 cheaper to maintain than humans cost, every organization, governmental or corporate, will have a huge incentive to replace humans with machines everywhere. Essentially, our ecological niche is, in a market economy, essentially an economic niche, and a cheaper human-equivalent AGI can drive us out of all of our niches.
Trying to get away from Amazon recently, I’ve moved to iBooks. Horrible. Apple is trying to push audio books on us and often only has audiobooks for certain titles, which you can easily miss. There’s a tiny little microphone symbol on the bottom right.
Is this being pushed by market demand or monopoly/duopoly influence.
That is interesting, because I find newer audio books to be much lower quality than those 20-30 years ago.
There are definitely plenty of products where the initial version was a high quality niche product, but once they realized there was a mass market, they realized it was more profitable to mass produce somewhat lower quality versions.
I don’t know if that’s what’s gone on with audiobooks - its not obvious to me whether there are lots of books whose audiobook market is large enough to be worth making a low quality audiobook for, but small enough that they can’t profit as much off a higher quality audiobook.
yeah that is probably what has happened. 30 years ago not everyone was walking around with a listening device, and listening to things constantly.
I tried one audio book and it didn’t appeal to me. But I have a long history of enjoying actual reading so I’m probably biased. I’ve heard of people consuming audio books at x 1.5 speed for efficiency. Maybe it’ll the future of information consumption. Doesn’t seem like it would work very well for novels though.
Faster speed works fine f you don't care about the details or don't want to think too much about what you are consuming. Just like for books.
I always find the people who are like "I can read 200 pages an hour", mostly aren't getting very good comprehension except on the broad points.
Similar with 2X on audiobooks. If I am reading some non-fiction book and feel like the author is getting repetitive, or needlessly going through multiple examples that only reinforce their point but don't change it. Then I will go to 2X sometimes.
Other times if something is really complicated or I want to think about it and react/critique it, I might re-read/re0listen several times at a normal speed.
I appreciate the quotes around "read." I agree: having books read to you isn't reading any more than watching a movie based on the book would be.
Except, ya know, how the words are 100% the same in the audiobook...
I don't know, it isn't the same, but it is 90% of the experience, especially in non-fiction where there is less "imagining" going on while you read.
Sometimes my face gets itchy when I feel socially embarrassed (often in a very minor way, like stumbling over my words a bit). I see other people scratching their faces in ways consistent with something vaguely similar. Is this a well-known phenomenon? Why does it occur?
There’s a known “stress grooming” response in animals, and I’ve read claims that face touching unders stress is similar. Pro tip: if you are in an escalating conflict and your opponent is touching his face, move - he’s about to sucker-punch you.
I remember a PUA blog once urging males not to scratch themselves in social situations, claiming that it is a primate instinct for grooming away bugs. It's a beta move, supposedly, signaling a lack of confidence. I don't entirely understand the logic, but it is interesting that you notice a correlation between social embarrassment and scratching.
I think there's a desire to hide your face when you're embarrassed so that people can't read your expression. You can't just cover your face with your hands, but scratching is a somewhat socially acceptable way to at least cover part of it temporarily.
This may be related to perspiration, and possibly personal acclimatization. I'm generally used to warmer temperatures, and sweat freely in the summer without particularly noticing. But the first vigorous exercise outdoors after winter, when ambient temps have first increased, isn't very comfortable.
I feel like I'm missing the experience of learning things together, brainstorming, and solving problems that I had as a student. I want to learn something that is outside my current expertise and especially not related to my job, and do it socially. How would I go about it? I had an idea about collecting a group of like-minded people and, like, just going through a textbook of something (I thought some introductory physics, because I don't know it but I'd like to), solving problems together. I don't know who'd be interested in that, though, especially how to find interested people offline. Do you sometimes have this urge so study some random stuff socially? How do you go about organizing that?
If you can find trustworthy pop history and science books you could arrange a nonfiction book club. Easier to recruit people for that than for reading textbooks.
I think that you can at least find that for theology pretty easily. I'd expect any evangelical church to have a pretty serious Bible study group. Mine is quite serious, and I think it would be easy to do.
Aside from that... I know someone who went to "atheist church" where they would have lectures about science. I think that the trick is probably to make it an identity thing in addition to a learning thing.
I have no recommendations to offer. But I wanted to voice a similar urge. I once had this idea of nerd/geek summer vacations where you spend a couple of weeks going in depth into a topic with a good teacher and many fellow students. This happened when I was on the staff at the Vanderbilt Free Electron Laser. And during the summer I could sign up for the Stanford Particle Accelerator School. OK that's the name I remember, but this is all I could find on the web. https://uspas.fnal.gov/ So maybe the name changed? Anyway it seems to be what you would like... but you'd need some different topic. (This was sorta a graduate level course in physics.)
I might suggest online university lecture notes in preference to a textbook.
I subdue that urge with MOOCs (e.g. Coursera/EdX/etc). Unfortunately while there are great courses for certain topics (Programming/Data Science/General Business) there is a real lack of content for other courses. Sometimes I'll just look up the syllabus for a course that sounds interesting from one of my old universities, and then informally try to follow along week-by-week. Truthfully though, I find it very hard to commit to just reading textbooks and doing problems, particularly for harder subjects. You can also find a lot of great lecture series on youtube by professors, that's a bit easier to commit to. Lastly, consider just enrolling in classes aimed towards adults. Sure it might be a couple hundred dollars per class, but it's not really that much on a per-class basis
I feel like the social part is important, though. It would really help with being committed to the studies, and just having more fun because some stupid instinct in my brain says it's not fun otherwise. I'm thinking in the direction of gathering some friends, but I don't have enough weird/technical/nerdy friends I guess...
I've tried assembling my regular group of friends for various types of activities (book clubs, physical training programs, etc.) and it's never worked in my experience. Even in university classes half the people there aren't really interested in the topic. IMO your best bet would be to either enroll in adult classes, or depending on the subject you may be able to find some already-existing community. If you live in a large city I think there's a decent chance you can. For example where I live the public library system organizes book clubs, workshops, and even public lectures from time to time
Covid origins
How do you decide when to have a debate? Why this year, rather than last year or next year?
It appears to me that there are two arguments for lab leak (1) proximity; (2) spies say so.
In March, Congress ordered the spies to spell out what they're talking about, so this might be an inflection point. If you want a definitive answer, waiting until after this happens might make sense. But you might instead want to see if you can predict this update.
I was skeptical that Congress and Biden have any power over spies, but the recent release of the names (as opposed to just the count) of WIV workers allegedly hospitalized in 11/2019 suggests that there may be an effect.
I don't know. Saar made the challenge and I'm taking him up on it.
I would not have taken the challenge in 2020 or 2021 because I hadn't seen enough evidence either way.
If I waited several years in the future, and it became 100% conclusive, one way or the other, then I also wouldn't take the challenge -- no one would host a debate on a settled issue.
At this point I think the evidence is in favor of natural origin but the public perception is trending in the opposite direction. I think there's a lot of misinformation floating around. I think there are few good summaries of this available for people who don't want to read lots of papers on the subject. So the prospect of debating it sounds interesting and I'm hoping the results are useful and informative, however the judges decide.
This is already a solved problem and there is a clear and very well detailed research history and funding history which led to the lab development and leak of the virus. They had war games on it, it has clear markers of genetic manipulation, a decade of published papers. It is amazing to me how effective their rather simple strategy of having project mockingbird style ‘news’ and government organisations repeat a lie over and over again.
On any other topic this would be clear, even OJ Simpson’s trail of blood to his house, motive, and a rare expensive glove we’re not as obvious as this. Truly I’ve never seen such an incredible amount of people talking themselves stupid in the face of insurmountable evidence since the Iraq war.
The reflexive lurch to listen to any authority figure one can find is rather at odds with what I understood the rationalist community to be about. You can go read the papers yourself, they published and were concerned about their sars research for over a decade, it went offshore to China at the WIV due to Obama’s bans etc. The research from UNC was key to this and you can see the insane, immense, incredible conflicts of interest Fauci and others had and how those without such conflicts such as the former cdc director have testified to Congress about the lab leak as the cause.
In what other topic would you look to those whose reputation and personal history was so tied to an outcome for the truth? Should we go ask the mafia about if they committed crimes or if their shoot out with many stray bullets caused the death of the child who lived on that street? Why is everyone so seemingly blind on this topic? A tone and narrative were sets early in complete contradiction to he evidence in a cover up and with bribes, and that isn’t a red flag to anyone? Read the emails yourself, look to the Twitter files…amd wonder why such a huge operation would be needed if it were zoonotic?!
Have you read Fauci’s emails? Foia obtained which show he literally had an overt pressure campaign to get key early publications and experts to flip the script, who then got large grants from Fauci and big pharmaceutical shortly after? The cover up is clear, the lies, the history, the complete and total lack of a zoonotic trail of bio similar strains across China and Vietnam, all despite those bat populations being well monitored?
Truly only an overwhelming lack of curiosity and attention to detail could lead to viewing this as a debate. It was most certainly a lab leak, there is a mountain of evidence vs a plume of empty conjecture in the media and by those who committed this crime against humanity.
Truly the most successful conspiracy has been the project mockingbird style effort over many decades by those in power to convince us that they never conspire at all and you’re crazy for thinking the aristocracy with their millennia of plotting and lying and killing would ever continue to do what it has always done.
As far as I know the only “clear marker of genetic manipulation” was some stuff that was claimed in a viral article of May 2020, which turned out to be missing a lot of statistics on other coronaviruses that turned out to make these not clear markers after all.
Agreed, SARS-CoV-2 doesn't have any clear markers of manipulation
What spies and when?
American spies. "Spies say so" is a an argument some people make, but I put zero weight on it. What I actually mean is that spies leaked details that I cannot access. In particular, as I said, they claimed that three people from WIV were hospitalized with respiratory illness in 11/2019. Big if true. This was first leaked two years ago.
https://www.nbcnews.com/health/health-news/u-s-intel-report-identified-3-wuhan-lab-researchers-who-n1268327
To a first approximation, the FBI in February 2023 (really, probably before that but it took a while to release the information). Several intelligence agencies have weighed in on the "lab leak" hypothesis, some pro and some con, but all at "low confidence", which is spy talk for "educated guessing". Only the FBI came back with a "moderate confidence" assessment, which means "no smoking gun but there's real evidence here", and their moderate-confidence assessment is that it was probably a lab leak.
They haven't explained why in their unclassified reporting, and I haven't read their classified report.
Here is an official document published, I believe, in 8/2021 already claiming that one agency put moderate confidence on lab leak.
https://www.dni.gov/files/ODNI/documents/assessments/Unclassified-Summary-of-Assessment-on-COVID-19-Origins.pdf
Thanks; I saw that when it first came out, but had forgotten it was that far back. Though the FBI apparently wasn't willing to put their name on that in public until later.
Presumably low confidence in a lab leak is high confidence in zoological origin. Those being the only two options. If so then the agencies are saying it isn’t a lab leak.
What Fred says. If it *did* work that way, we'd be implicitly at four high-confidence votes in favor of lab leak vs only one against. But in fact spies and spymasters in competently run intelligence agencies are allowed to say "we don't know"; they don't have to add up to 100% confidence in everything. An assessment of "X with low confidence" means, or is supposed to mean, that X is more likely true than not, but at maybe 60/40, not 80/20 or 90/10.
Lab leak *is* zoological origin, apart from some tiny hypothesis that is quite far out there. The question is whether the animal that infected people did so in a lab or in a market. (It doesn’t seem likely that the animal infected a person in the wild.)
Why do you think the wild is ruled out? What would it look like if a bat encountered a human in rural Hubei? Wouldn't it look like an outbreak in a population center? In fact, the Chinese government claims that there were many cases in Hubei but outside Wuhan in 11/2019. Big if true.
I don't think it's ruled out. But it does seem unlikely, given the strong evidence that the wet market was an early superspreader event (and weaker evidence that two lineages of virus were present next to animals there), as well as the suggestions that there may have been people at the virology institute that were early cases. It would be extra-coincidental for *both* of those to have so many apparent early cases if the actual origin was elsewhere - but it definitely isn't *completely* ruled out!
No, that is not what that terminology means. "Low confidence lab leak" does indeed mean that they think it's more likely than zoological. It just indicates uncertainty. (And a third option would be not having enough information to feel comfortable issuing even a "low confidence" statement).
I'm always so flabbergasted that people care *so much* about the origin of Covid. Like, it's interesting on some level, but both proposed sources are obviously realistic and we should be doing our best to address both regardless of where this particular virus came from.
I deny that the lab leak origin is realistic. To the extent that it's being used to argue against research on potential pandemic viruses, it's important to debunk. People are of course free to argue that gain of function research is dangerous and should be banned anyways, but they don't get to use COVID as evidence.
Do you mean to say that lab leak is unrealistic in general, or just unrealistic as an explanation for this particular case? The former would be an extraordinary claim, and needs more backing it up than "I deny". The latter is at least plausible, though I think unwarranted given the evidence. Both hypotheses remain plausible w/re COVID-19, IMO.
I think by "realistic" I mean "realistic vectors for infectious disease", not so much "realistic as a source for Covid". Though, I don't care enough to do a lot of investigation into whether it is or is not a realistic source for Covid based upon available evidence.
I’m not sure you understand, the gain of function research continues and will lead to a second covid which may be much worse if it is allowed to continue. Would you apply this to other crimes? Should we just have let a serial killer go since the dead are already dead? The lab leak means we neeeed to rethink and ban many forms of research. The zoonotic view means nothing.
I'm not claiming that GoF shouldn't be stopped or regulated in some manner.
I'm claiming that GoF should be stopped or regulated regardless of whether its the source of Covid.
Lab leak *is* a type of zoonotic origin. Both versions of zoonotic origin suggest extra care working with wild animals. One suggests stronger regulations on markets for exotic animals. One suggests stronger regulations on lab research of wild animal viruses.
You’re misunderstanding the GP, they understand that GoF is dangerous. As is zoonotic origination of pandemics (eg wet markets). Ie there are risks from both.
I think your crime analogy is the exact opposite way we should be thinking about it. Regardless of whether it was actually a lab leak, on inspection it turns out that GoF _could have_ caused the global pandemic.
We might care about the historical facts if we were going to assign blame/liability, but as far as preventing potential future lab leaks it’s irrelevant.
I view the lab leak stuff as mostly important inasmuch as it’s exposing details about how cavalier GoF research is, and how critical it is to regulate/ban it. Actually assigning blame for any leaks is not gonna happen and is a waste of time IMO.
So you don’t think there is any value in deference then?
Let’s assume this was down to risky behaviors at the lab which caused all this. Does having a forgive and forget attitude send incentives to future labs about how to handle risks?
(Assuming typo deference->deterrence?)
I don’t think deterrence is particularly relevant here. This isn’t rogue individuals or labs researching GoF where we cannot control their actions except by threats. These are all (AFAIK) labs with government grants. If NIH decided to forbid grants for GoF or even to labs doing that work, much of the work would stop.
The Wuhan lab was collaborating with US researchers and got some funding from the US (though it seems maybe not the majority of their funding?).
To be clear I think some mix of restricting funding and imposing safety requirements as preconditions for grants, and academic norm shifting around this would be required to fix the risks. There is some risk you could squash in, say, China by having a stronger threat of consequences, but I think most of the probability density of a future GoF leak is from labs we directly fund, and most of the risk reductions available outside that are more achievable by academic norm shifting than by threats.
(Perhaps you can be more clear about what deterrence specifically you think might work, and how you’d implement it though? Sanctions on China? Cut ties/funding with Chinese labs?)
Sentences for the UD and Chinese funders of the lab? A full investigation by outside parties?
There seems a very no-zero chance that this was actively covered up with the help of Fauci and people who signed/wrote sole of those initial )this was definitely not from a lab) letters. All of them should be investigated and if guilty put in jail and stripped of any ability to touch a lab or any funding from the government.
I like John Stewart’s take on the issue. “If there is an outbreak of chocolatey goodness in Hershey Pennsylvania, you should probably not overthink it.”
In a wet market, and in the city of a biolab, suggests that we should regulate both wet markets and biolabs.
What if outbreaks of chocolatey goodness are ubiquitous in nature and have happened hundreds of times for the entire history of humanity, and precisely zero of them have ever had an artificial origin? In that case, "not overthinking it" would mean assuming a natural origin.
What if the outbreak of chocolatey goodness happened 0 meters from a known natural source of chocolatey goodness, and 11 miles from the nearest factory? In that case, not overthinking it would also mean assuming a natural origin.
Yeh the distance between the market and the lab is significant.
>and precisely zero of them have ever had an artificial origin
But that's not the case here. There have been a number of disease outbreaks caused by lab leaks in recent history. The 1979 anthrax outbreak in Russia, for one.
None of those were of novel viruses that nobody had seen before. Everyone knew what anthrax was, and that many labs were studying it.
So your argument is that it's possible for a novel virus to be made in a lab, and also possible for a virus to leak from a lab, but the idea that the same virus could both be made in a lab and then leak from that lab is ridiculous?
I mean, the fantasy scenario is that we prove it was due to Chinese governmental malfeasance and this helps to bring down the Communist government, just as Chernobyl (supposedly) did in the USSR.
It's probably only a fantasy but you can't blame people for wanting it.
The communist party is pretty popular in China. Also the malfeasance would be local to Wuhan. Beijing acted pretty quickly.
TBH, I don't really see people making that argument when arguing about the subject. That being said, I don't really read people arguing about the subject that much.
I do grant that if you care about the subject a lot because you think it will make a meaningful difference to the people who have a chance at bringing down the CCCP, then that might hold water. I would however ask a person what other actions they're devoting as much resources to as they are to their arguments about the Covid source to bring down the CCCP...
ETA: It seems a little 4D chess to me, so even if that is a person's true treason for caring, I'm skeptical as to it's efficacy.
I agree with you in principle but for some reason the likelihood of gain of function research getting restricted seems to hinge a lot on the outcome.
I agree that may be the case. I view these as all plausible outcomes:
1. Proven to everyone's satisfaction that it leaked from Wuhan: resources devoted to GoF research control goes up, resources devoted to control of natural sources go down.
2. Proven to everyone's satisfaction that it is from natural sources: resources devoted to GoF research control goes down, resources devoted to control of natural sources goes up.
3. Moving on from proving one or the other: resources for both scenarios go down.
4. Moving on from proving one or the other: resources for both goes up.
5...a bunch of other scenarios
My theories of why so many people care about this:
1. It's become a sport of sorts.
2. They genuinely think that proving one way or the other will improve the outcomes in the future.
3. Some weird nationalism thing.
I think all of those are mistaken.
Perhaps some guy just wants to be the first person to win 100 grand for winning an internet argument.
At least part of the reason I care is that I am offended by people arguing, for quite a while successfully, that one should ignore the overwhelming evidence for a connection to WIV, evidence we had from the very beginning. There were, so far as we know, only two labs in the world doing gain of function research on bat viruses and a bat virus that could have been produced in such a lab appeared in the city where one of them was located. A live market was also located there — one of thousands. A different origin isn't impossible, but the actual treatment of the issue was brute unreason supported by claims of authority, which offends me.
Beyond that, if it was a lab leak that's a strong argument against doing that sort of research.
I’m not sure if we can trust any authority on the matter. In 2020 experts rushed to tell us that the virus could not be lab grown.(not that it was unlikely but impossible).
A year or so later that changed, now the pendulum swings back to not being a lab leak.
I'd argue that it being a lab leak is just an incremental reason amongst many against doing GoF research.
Also note that I'm not saying it's irrational to care, I'm just arguing that many people seem to care *too much*. The world which we should aim for, one with restrictions on GoF and research/controls/acknowledgement of natural sources is not changed by the answer to "where did Covid come from". I don't think it's obvious in any way that a world where we find out for sure where it came from is meaningfully safer because of the numbered list I gave in another comment.
I certainly understand your offense. I don't know how much effort, money, or resources you put into arguing for one source of Covid, but AFAICT, from an objective standpoint it should be very little resources.
I'd also argue that often the lab leak discussion lacks any nuance (on both sides). Consider the following range of options (on a scale from (1) least lab leak to (10) most lab leak):
0. Covid was actually caused by the US/CIA etc
1a. Covid did not originate in Wuhan (but was brought to Wuhan by visitors from another part of China for reasons completely unrelated to WIV)
1b. Covid originated in a wet market in Wuhan Market from an animal brought to Wuhan unrelated to WIV
4. Covid was brought to Wuhan by lab personal/related persons due to a trip to other parts of China where there are bats with viruses
5. Covid originated in a wet market due to animals brought to Wuhan in conjunction with the WIV (e.g. bringing some bats for WIV some for the market)
6. Covid originated due to an individual infected at WIV while dealing with bats but not viral research
7. An animal from WIV was later sold to the wet market
8. Covid originated due to an individual studying Covid at WIV (no gain of function but having known about the virus)
9. Covid originated through gain of function research from a less infectious version
10. Covid was deliberately released from WIV
Of these
0 and 10 are both extremely unlikely (if anyone wants to bet on evidence of either of these appearing in the next year let me know)
4-5 are the most probable to me
6-10 are what I would consider to be LAB LEAK but I think people can mean anything from 4-10
Only 9 has a meaningful impact on what we should do going forward (evidence against the utility of gain of function research).
I was a little imprecise in the comment you're replying to. I should have said "why so many people care **so much** about this".
Government officials with ties to the Wuhan lab worked with giant corporations to stop people from talking about whether this thing came from the lab. Is that really so flabbergasting?
Caring as much as some subset of people do about the origin of Covid is not exactly the same thing as caring about lies about the origin of Covid.
Just from watching the structure of arguments about this thing, I posit that most people who care about lies about the origin of Covid only do so in service to the first thing.
It’s only natural for people to be concerned about something that disrupted over a year of their life and might do so again.
It’s also natural for people, in response to “we might be lying to you but you’re the *problematic* one for being *overly concerned* about it”, to respond with vitriol that would be unacceptable in these comments.
This is somewhat true, but I don't think really addresses the root of the issue. Of course I'm aware that people aren't 100% rational and I'm not actually flabbergasted when people act irrationally.
If we restrict the word "flabbergasted" to only those times where people are acting irrationally *and* they're doing so when it's not expected for some percentage of people to act irrationally, then I'm not sure the word flabbergasted would ever be used.
> t’s only natural for people to be concerned about something that disrupted over a year of their life and might do so again.
Agreed. You'd hope that they'd be concerned about the parts of it that actually matter, though.
> It’s also natural for people, in response to “we might be lying to you but you’re the *problematic* one for being *overly concerned* about it”
I don't think *They* (government, corporations, etc) are actually making this claim to any substantial degree and even if they are, people arguing about this don't seem to mostly be responding to that.
"You'd hope that they'd be concerned about the parts of it that actually matter, though."
That's the thing though, the people that created and implemented the lockdowns ARE what actually matters. If someone thinks it's ok to shut down a country/arrest noncompliers/render dissidents unemployable because they've got really good reasons, it's important to understand exactly how they're going to evaluate evidence and how honest they are going to be about it.
I challenge you to poll these people and find out whether your intuition is correct. I am happy to place a bet that if you ask people directly they’ll tell you they are furious about being lied to and told they were racist for considering a plausible hypothesis. For a lot of people, this episode was the clearest example of how large categories of institutions are corrupt.
Remember kids, the outbreak is from shoddy hygiene and lab practices in Chinese bio labs = you are an arch racist.
But the outbreak is from shoddy hygiene practices in gross Chinese wet markets = “the science” and “cultural sensitivity”
Don’t commit thoughtcrime!
Unfortunately, I don't think I care enough about the subject!
Well, regardless of the method the "who" responsible is the CCP (though, speaking of 'who', the WHO didn't exactly cover itself in glory).
Motive matters. I’m sure the Wuhan virology researchers were trying to speed up progress on treatments/vaccines in the event of a zoonotic pandemic. The crime might be taking too many risks in this attempt, but the research seems to have been risky regardless of whether it actually caused this pandemic.
1. I didn't claim that you shouldn't care.
2. The extent we should care should be largely mediated by the benefits we can get out of the caring.
I care who committed 9/11 and JFK to some extent, but many people care about those things too much!
Holding those who covered it up (and ANYONE who defended them) accountable for the crimes against humanity they committed.
Recently watched M3gan*, a comedy horror about what's basically a ChatGPT killer robot. Was wondering if any of the more invested AI folks had opinions on it with regard to the general AI conversation.
*(Incorrectly pronounced 'Megan' by everyone in the movie; it's clearly M-three-gan.)
I thought it was hilarious.
Zvi wrote a review of it a while back that you might be interested in: https://thezvi.substack.com/p/movie-review-megan
Is M3gan a relative of GlaDOS ? :-)
The trivia actually says yes:
"M3GAN's voice is modelled, in part, from another famous artificial intelligence-gone-rogue, GLaDOS, from Portal (2007). This is most noticeable during scenes when M3GAN's voice is auto-tuned in order to sound 'glitchy'."
Many Thanks!
I thought it did a good job of showing how hard it is to alignment an AI with human values. They showed that seemingly innocuous instructions to a doll end up bad if the doll is very capable.
I wish they had done more to show how complex the decision of whether to pursue advanced AI or not is. In the movie, it was pretty clear that Gemma should pause on the development of M3GAN. You could come away from it thinking, "Let's just not pursue advanced AI". I wish they had made the arguments in favor of developing advanced AI more real (like had the same tech used in curing cancer or something). That would have made the decision much harder, and I think showed how hard this whole thing is and why we're unlikely to not do it.
If you're interested, here are some thoughts I wrote up when I saw it: https://thegreymatter.substack.com/p/assorted-thoughts-on-m3gan
Re your first paragraph: "Computer, in the Holmesian style, create a mystery to confound Data with an opponent who has the ability to defeat him."
I enjoy both horror and AI :)
I would say that it didn't have much to say about existential AI threat or the technologies as they exist today; the slasher horror aspect of the movie was pure killer robot fun without much in the way of new ideas.
What I did find inspired was the idea of AI companionship as a superstimulus – something more gratifying, intimate, and risk free than messy human friendships. I think that's a genuine danger, and would be surprised if this isn't a significant part of the discourse in five to ten years.
> Incorrectly pronounced 'Megan' by everyone in the movie; it's clearly M-three-gan.
Are you familiar with the movie Se7en?
And Thir13en Ghosts
https://m.imdb.com/title/tt0245674/
Ya, Se-seven-en is great.
Shouldn't the progressive/woke concepts of 'privilege' and 'oppression' include the people of Ireland and Scotland, who were brutally repressed by the English for centuries? Haven't the Irish in particular been subject to even more oppression than say other British colonial subjects? If I'm not mistaken the colonization of Ireland went on for much longer than India or the Caribbean or elsewhere. (Or much longer than Africans were enslaved in the US or elsewhere, for that matter). Yet we don't see Irish as an official Oppressed Category the way we see other racial groupings, etc. Has anyone on the progressive side ever addressed this or thought about it?
Assuming you are US-centered in making this point, I think it’d be valid if there were any ongoing detriment to being Irish in today’s society - if it were harder to get a job with “O’Malley” on your resume, or if there were an “Irish/White wealth gap,” or if police arrested or shot unarmed Irish disproportionately to other groups, and so on.
At present I’m unaware of any such race prejudice existing with respect to the Irish, though.
I honestly wouldn't be shocked to find out that all of those things were about as true for Irish as for black Americans...
As an example, a study found that there remains a significant wealth gap between Norman-descended English and Anglo-Saxon-descended English, almost 1000 years after the Norman conquest
I have specifically heard progressives from the UK talk about this, yes. Americans care about American causes of oppression.
Anyone who talks about intersectionality recognizes this. There’s a lot of people who occupy privileged categories in one hierarchy and oppressed categories in another. Whether it’s Jewish people, Irish people, white women, rich cis gay white men, etc.
Some people like to caricature intersectionality as a simple additive model of oppression, but that is precisely the *opposite* of intersectionality, which is all about how *intersections* often function differently from how either category functions alone.
Look up the field of black male studies for an example.
This should by now make it obvious that you can't measure privilege and oppression, you can't know someone else's experience, and the degrees projected are arbitrary.
Can't comment on British progressives, but I think that people in the US as a whole simply do not care enough about foreigners to bother thinking about it
Another thing to consider is that there was significant settlement in Ireland by English colonists during the Ascendancy. A portion of modern Irish ancestry is English, to some extent the modern Irish are English. So it's a bit like asking whether Australians should be considered oppressed. The aborigines probably should, but the English diaspora shouldn't. Except in the case of Ireland the two groups aren't easily distinguished and have mixed.
Oh the mixing wasn’t all that. After the reformation it largely disappeared. Irish people have as much English heritage as American blacks have white heritage. Or less.
In places like Northern Ireland the English/Scottish did in fact become the majority, but clearly no ethnogenesis took place.
"Irish people have as much English heritage as American blacks have white heritage."
Have you got a source on that? From the genetic studies I've seen, which groups in the British Isles have what ancestry is still a fairly open question.
I have the entire history of Ireland as a source for that.
What you need to prove is the opposite - the claim that an ethnic group is largely the same as another is the extraordinary claim.
Scots are mostly Irish immigrants who displaced the Picts.
As someone replies below - this is driven by US history not the reality of any individual European country. But this is true of the entire use of “white” outside of US discourse, which bleeds into British media.
Here’s a woman upset that audiences at a Scottish festival are … Scottish.
https://amp.theguardian.com/stage/2022/sep/01/south-asian-critic-edinburgh-fringe-diversity
(But of course she says white, not Scottish)
Assuming the statistic given in the article of 99% of the audience members being white is correct, that is actually quite a bit higher than the proportion in Edinburgh in general, at 92%, so it's not like that's an entirely trivial concern. She does also seem to complain about the lack of ethnic diversity in Edinburgh in general though ("While it might be a stretch to expect the Scottish capital to match the diversity of London, with a face so markedly different, you cannot help but feel isolated."), which is a weird complaint.
Her 99% is probably an exaggeration though and it’s not just people from Edinburgh who go to the festival. If it was only Scottish people then white people would be 96% of the population.
It’s basically a metropolitan sneer - why doesn’t Edinburgh look like London.
Irish, like Italians, used to be 'black' (or Black, if you believe the NYT). After enough died in mines, on railroads and in factories, the protestant majority decided they could be white -- exposing the whole concept of "race" as bogus.
The calculus for caste is mutable.
That's not true though.
Citation needed. When were Irish considered black, and where is the evidence for it?
I didn't intend the literal color, but the caste. In the Anglo-centric mind set, the Irish and Italians were regarded inferior castes. African-Americans have suffered the same fate.
Recently, I viewed a news clip about a man who oversaw the launch of one the world's most advanced telescopes into space. The man happened to be 'black'. I viewed another report about a university provost who oversaw an Ivy League school his enslaved ancestor helped build.
Are they still 'black'? Or is it now the family from Venezuela? Race is a social construct, and racism is ultimately about caste.
I recall that one of the examples of the Irish having been considered black given by Noel Ignatiev - who popularised the concept - was a historical reference to the Irish as "white n*****s". Make what you will of that.
Yes, Noel Ignatiev was the one who invented the idea that the Irish were not considered white. He invented the idea in the face of overwhelming historical evidence to the contrary: https://www.washingtonpost.com/news/volokh-conspiracy/wp/2017/03/22/sorry-but-the-irish-were-always-white-and-so-were-the-italians-jews-and-so-on/
"
Here are some objective tests as to whether a group was historically considered “white” in the United States: Were members of the group allowed to go to “whites-only” schools in the South, or otherwise partake of the advantages that accrued to whites under Jim Crow? Were they ever segregated in schools by law, anywhere in the United States, such that “whites” went to one school, and the group in question was relegated to another? When laws banned interracial marriage in many states (not just in the South), if a white Anglo-Saxon wanted to marry a member of the group, would that have been against the law? Some labor unions restricted their membership to whites. Did such unions exclude members of the group in question? Were members of the group ever entirely excluded from being able to immigrate to the United States, or face special bans or restrictions in becoming citizens?
If you use such objective tests, you find that Irish, Jews, Italians and other white ethnics were indeed considered white by law and by custom (as in the case of labor unions). Indeed, some lighter-skinned African Americans of mixed heritage “passed” as white by claiming they were of Arab descent and that explained their relative swarthiness, showing that Arab Americans, another group whose “whiteness” has been questioned, were considered white. By contrast, persons of African, Asian, Mexican and Native American descent faced various degrees of exclusion from public schools and labor unions, bans on marriage and direct restrictions on immigration and citizenship."
And even if the Irish, etc, were not considered "white", it would not follow that they were considered "black". Other categories can in principle exist, and it is pretty clear from history that the Irish were never in the same category as actual blacks.
I don't know how coherent these concepts are, but if I'm going to steelman privilege/lack of privilege, I'd say it's supposed to be based on the magnitude of the current disadvantages groups face from past oppression, versus the magnitude of the actual oppression itself. If the Irish have recovered from their oppression more than other colonial subjects, it makes sense to say they have more privilege.
I think this is an effect of American cultural hegemony. While the Irish faced some discrimination in the US, they've been part of the ruling coalition since the beginning of the 20th century. In addition Ireland had a unique oppressor (only one) and doesn't have a common relationship with the other colonies so there's no block arguing for reparations and no weak links who grant concessions. See also the Basques, Catalonia, Quebec, Taiwan, the Copts. In general past internal oppression is not a major focus for Americans if it doesn't map to American racial groups.
I was late to the last open thread, so I'm just going to try this one more time. There's a market on Manifold that can't resolve until an independent mathematician weighs in. (Or a consensus is reached, but that's clearly not going to happen.) Here is the market: https://manifold.markets/dreev/is-the-probability-of-dying-in-the
Does anyone have advice for how to find an expert, or perhaps an alternative way of resolving the market?
Speaking of markets on Manifold that can't resolve yet: Does anyone here, preferably someone based in Africa, know the results of Sierra Leone's parliamentary election on Saturday June 24? I need to resolve https://manifold.markets/duck_master/whats-sierra-leones-political-party (since I really like making markets about upcoming votes around the world). I've been *completely unable* to find stuff about the parliamentary election results on the internet, though the simultaneous presidential election has been decently covered in the media as a Julius Maada Bio win.
(I copy-pasted my comment from the previous open thread because I'm lazy.)
It's actually possible to fairly resolve the market without figuring out if the 1/2 argument is correct:
* The 1/36 argument is correct, obviously - there are people arguing that 1/2 is correct, but I didn't see anybody point to a mistake in the argument that 1/36 is correct.
* The 1/2 argument is either correct or incorrect.
* If it's incorrect, then resolve the market in favour of the 1/36ers.
* If it's correct, then 1/2 = 1/36, and with a bit of algebra we can deduce that all numbers are equal. So simply resolve the market in favour of the 1/36ers, then give each 1/2er zero manifold play money - which happens to be equal to the amount they would have won if the market were resolved in their favour.
This is a stupid question and I am annoyed at how I had to find out. I first really quickly skimmed the market, and decided A) The answer is obvious and I don't understand why anyone wouldn't get it and B) I bet I can code up a really quick argument by example.
I code up a test and run 500 iterations, then realize "wait, unless I'm misunderstanding something, no one could not get the answer". That's when I realized I had wasted my time (admittedly only 5 minutes, but still)
I got back and re-read it and realize it's a stupid semantic debate about _when_ you should calculate your probability, and who exactly is doing the calculating and out of what pool.
It is obvious that, in hindsight after the game concludes ~50% of the players will be dead, but, at the time of the individual roll, you, in that exact moment, have a 1/36 chance of dying. So which answer is correct depends on who is asking and when they are asking, and also plays around with ambiguities about infinite pools of people etc.
Because the potential pool of players is infinite, and you can't know how long any individual round will go, you can't know ahead of time what your odds of dying are, because there is no denominator. After the fact, 50% of the people who got selected are dead (although out of an infinite pool). In the exact moment of any individual role, there is a 1/36 chance of dying
The question is too ambiguous and can't be resolved.
My personal opinion on how the ambiguities _should_ be resolved is that it's 50%. Because it says "given that you are selected to play". Of the pool of people selected to play, 50% of them are dead. This is who "you" should mean, in my opinion.
However, I can see how someone would interpret it differently.
From reading through the thread I don't think you'll find a mathematician who will satisfy both parties. The original bet/prompt simply wasn't specific enough. At some point people are debating what counts as a probability system...
IMO your best bet would be to propose randomly emailing a few mathematicians working in probability theory (independently), and employing them to come up with an answer and just agree to go with the majority
Let Joe Blitzstein resolve the market. He loves probability and paradoxes.
With infinite people, isn't he probability that you actually play 0?
Yes, and that’s an important consideration in this. Hitchcock and Bartha show that, on a reasonable calculation of uniform probabilities on an infinite set (which don’t literally make sense, but this case involves) conditioning on the fact that you are in the room changes the probabilities, and even gives a specific finite probability to the claim that the game took infinitely many rounds:
https://link.springer.com/article/10.1023/A:1005100407551
looks interesting... but not 39.95 interesting.
Sci-hub may have it
It's unfortunate that academic journals have this sort of fee structure. If you have university library access, there should be a way to get this. If you're interested enough, you can e-mail me (last name at gmail) and I can send you a .pdf.
That's addressed in clarification #3 on the market's description. It's not actually about an infinite number of people, it's in the limit as the number of rounds (and therefore the necessary size of the initial pool of people) goes to infinity, where if nobody dies after the round limit runs out, everyone goes free. In this case, it's perfectly well-defined, and the answer is 1/36. [edit: This originally said slightly more than 1/2. I realised my mistake after trying to actually do the calculation explicitly.]
this limit is zero, i was just phrasing loosely.
as the number of people go to infinity, the probability of being chosen goes to zero.
for any fixed finite number of people, the answer is 1/36
There's a crucial difference between it being 0 and tending to 0 though, because the answer, as a conditional probability, is the ratio of two values both of which tend to 0. The limit is well-defined but 0/0 is not, like a derivative. I started to write out the explicit calculation for the answer to show why it's not 1/36 but it turns out I was wrong and it is.
This suggests a practical and undetectable way to help a 3rd party cheat at Monopoly:
* If you're told you have been chosen to roll the dice, find a Monopoly player who wants to roll a double on their next turn
* Convince their opponent to let you roll on their behalf
* Declare that this roll is also your roll for the snake eyes paradox game (if you don't say this out loud the dice might not realise that they are meant to come up snake eyes with higher probability)
* If the number of rounds was high enough, the Monopoly player's probability of getting a double is more than 1/2!
I am currently reading Deirdre McCloskey's "Bourgeois" trilogy which gives an interesting alternate perspective on the idea of moral decline. According to McCloskey, the Great Enrichment that began around 1800 was caused by a specific kind of moral *improvement*, namely the adoption of norms that encouraged what she calls "trade-tested betterment". Whether or not the difference is causal, she makes a pretty good case that there was a big contemporaneous change in moral attitudes.
This raises the question of whether the Great Stagnation in the West since the 1970s (the whole "WTF happened in 1971" complex of changes) can be traced in part to a decline in the cultural acceptance of these same norms. I would be very interested to see if anyone has tried to do a rigorous statistical investigation of this.
Can you summarise those norms?
I read Scott's Lorian Psychiatry on Depression, very interesting. What are the best resources out there for supporting someone with depression?
Do you mean things to read or ways to treat? Or specifically how to support someone else who has depression?
Combo of talk therapy and medication is most effective. In terms of medication, ketamine is promising alternative to SSRIs. I don’t know if Scott has written about TMS but it’s an option that’s neither medication nor talk therapy.
Exercise is hugely effective to do any amount and in any form. Lots of other lifestyle type changes can help too — things like art, gardening, music, dance, walking in the woods. Therapy groups can help. There are supplements like l-methylfolate that have a good track record.
If it’s someone else, listening non-judgmentally is good. Sometimes people need to just hear themselves say things out loud to spur action. Avoid using the word “should” with others. Sometimes it can be helpful to take initial steps with them — offering to help find a therapist or schedule an initial appointment with PCP to talk about treatment options.
I meant to say, supporting someone else who has depression. I agree with your advice in your last paragraph thx. I'd appreciate reading something in-depth, but the internet seems full of pop psy articles and I'm not sure it's scientific advice.
I’m not sure about the science of supporting someone who’s depressed but the advice from places like Mayo or Cleveland Clinic look fine to me.
I don't see anything on either site about supporting someone else with depression. Except for calling 988 988 on your phone to reach the Suicide and Crisis Lifeline I guess.
Is there any pushback to the recommendation of 1 or 1.2 g protein consumption per Kg body weight?
Don't know if you would call it push back, but here's a reasonably extensive review for bodybuilding
https://mennohenselmans.com/the-myth-of-1glb-optimal-protein-intake-for-bodybuilders
I don't eat that much as a vegan (I believe some serious vegan athletes might differ, I just do an occasional mini tri and was vegan while pregnant with twins and suddenly craved a LOT of tofu and edamame but wasn't precisely measuring at the time) but I don't believe 1 gram/kg is a requirement. I think you can spend a lot of time on the topic, but I've always found the UK vegan society did excellent research and they say .75
https://www.vegansociety.com/sites/default/files/uploads/downloads/Protein%20PDF_0.pdf
VERY SHORT ANSWER: Thomas, I believe the answer is: No. There's no justifiable pushback to 1.0-1.2g protein/day per kg bodyweight for people who have neither pre-existing chronic kidney issues (duh, obviously!) or established family-member-proclivities to kidney stones.
SUBSTANTIALLY LONGER ANSWER: In a moment I'll give 5 rules-of-thumb. Admittedly, I haven't looked into the evidentiary basis for the following rules of thumb, BUT:
1) First of all / "stay tuned" teaser: I will try to look into their evidentiary basis over the course of this Independence Day long weekend, AND
2) Even if I end up reneging on (1), I can say presently that the following 5 rules-of-thumb seem IMHO to come from trustworthy health science / exercise science popular sources, namely:
a) for the general health rules-of-thumb https://www.health.harvard.edu/blog/how-much-protein-do-you-need-every-day-201506188096,
and
b) for the explicitly bodybuilding (i.e., maximizing muscular hypertrophy while minimizing long term health damage from what's frankly a disproportionately body-dysmorphia-motivated sport) this following "Fitness Myths" installment from "Dr. Mike" Israetel who's a noted PhD-credentialed examiner of "bro science": https://www.youtube.com/watch?v=nkIKesKHIIE
Ok, without further ado, here's the rules of thumb that I think are accurate: <i>(ERRATUM 2023-07-02 2:20pm -- Speaking of "accurate", as Mallard helpfully pointed out in a reply below, I carelessly mixed up per kg and per *lb* a couple times in my original post, especially toward the end with rule-of-thumb #5. I think I've corrected all such kg<->lb mixups below, but as an extra check, y'all can apply the heuristic that protein amounts recommended below for normies are per *kg* whereas protein amounts recommended for *bodybuilders* are per *lb*.)</i>
1) <0.3g protein/day per kg bodyweight --- you very likely are going to suffer nutritional deficiencies
2) 0.8g protein/day per kg bodyweight --- this in fact is the current US RDA for *average* US adults (read: sedentary... but also, no chronic kidney conditions, of course). IIRC, this 0.8 figure was explicitly meant somewhat as a corrective to the notion that previous rules-of-thumb more like 0.5g per kg bodyweight probably nontrivially exacerbated the inevitable muscular atrophy over the course of middle age into one's autumn years... which indeed can get very bad in one's autumn years if you don't eat enough protein.
3) 1.0g/day per *lb* bodyweight --- The above-linked "Dr. Mike" YouTube's central point is that what's considered good research explicitly on competitive *natural* (no-PEDs) bodybuilders shows that, to first-order, muscular hypertrophy benefits essentially hit an asymptote at this level of daily protein consumption. (I phrase it as "what's considered good research" since I fear pitifully small sample sizes and or longitudinal-study-followup-times... also see comment #5 for "second-order" effects.) NB: This 1.0 g protein/day per *lb* bodyweight is *despite* many bodybuilders aiming for at least 1.0-2.0g/day per *lb* bodyweight.
4) 2.0g/day per *lb* bodyweight --- supposedly there are longitudinal studies (not sure if they're all explicitly "athletic" individuals or some sedentary individuals too) that people with no pre-existing chronic kidney issues can do this day-in-and-day-out for years with no significantly higher risk of incurring any kidney issues (maybe just chronic kidney issues, not sure about higher kidney stone risk... which IIRC does seem to have some nontrivial hereditary proclivities)
5) SIDENOTE on that Nota Bene "NB" in #3: I said "to first order" and also specified #3 really was in the context of competitive natural bodybuilding. I did this since there are "second order" caveats, though I feel all the ones I'm about to list (except for the first) are kinda more bro-science anecdata than really well established (by the standards of, again, probably small sample size / short longitudinal-follow-up-times common in exercise physiology journal articles):
a) It's widely believed --- almost assuredly wrongly --- that bodybuilders on anabolic steroids and growth-hormone-releasing peptides benefit from ingesting *more* protein than "natties" (natural bodybuilders). I say "almost assuredly wrongly" not only for what I believe is the existence of some directly empirical studies (though probably self-reported survey) on hypertrophy vs protein intake, but also what I gather is settled biochemical knowledge on some "micro" / in-vitro scale that those PEDs *augment* muscle tissues' ability to take in protein. Thus, if 1.0g per lb bodyweight seems the asymptote of utility to competitive natural bodybuilders (a la rule-of-thumb #3 above), then 1.0g per lb bodyweight should -- all other things equal -- be the asymptote of utility for PED users.
b) It's widely believed that bodybuilders in the throes of the final month or so pre-contest as they're "cutting" down to that freaky low-body-fat level benefit from like 1.25-1.50g protein per lb bodyweight both because (i) protein tends to reduce appetite and you will be dieting in ways that tax your willpower by just making you outright hungry and (ii) extrapolating from the same logic that leads to "protein-sparing fasting" for normie weight loss --- i.e., maximizing fat loss and minimizing muscle loss --- we infer that since bodybuilders want freaky weight loss --- i.e, LOTS of fat loss while simultaneously, at the very least, zero noticeable muscle loss if not praying still for some muscle *gain* --- they can benefit from more protein than the 1.0g protein per lb bodyweight per day.
c) A growing number of bodybuilders are vegetarian and even vegan. It's widely believed (again, perhaps just on the level of "bro science" that maybe won't pan out) that they benefit from aiming for 1.25-1.50g protein/day per lb bodyweight
In closing:
-- First, especially as a man carrying <ahem> a lot of excess body fat </ahem> a SANITY CHECK: Based on just my intuition, I kinda think "per kg bodyweight" should be probably replace by "per kg bodyweight were you 20% body fat, tops... maybe 15%".
-- I repeat that I really haven't checked the evidentiary basis of the above, but just broadly trust the popular science level links mentioned above, BUT...
-- ... I repeat that I will try to look at least some of that evidentiary basis over the course of this long Independence Day weekend.
I haven't forgotten my promise --- my perhaps impulsively-made, overly-ambitious / "how complicated could it be?"-style promise --- to look into the evidence for the protein rules of thumb I mentioned.
But now that I discovered it *is* somewhat complicated, I'll try to keep it brief and just give the following *2* points for a good gist for the moment:
(Point 1) Perhaps first and foremost, I've discovered that the main "recommended daily allowance" / "dietary reference intakes" / etc. that various government bodies in the US, Canada, Europe, etc make are very heavily based on the *objective*-in-principle-though-umtpeen-caveats-in-practice test procedure that goes by the buzzphrase of "nitrogen balance". That is, get a couple hundred or maybe even a few thousand representative adults in each age, sex, ethnicity, etc cohort. Put them on a controlled diet for a few days (5 days is good number) with various meticulously measured amounts of protein intake. Then meticulously measure <ahem> their feces and urine </ahem> to see how much protein they excrete. Run statistics to get some regression curve that allows you to ideally interpolate, but maybe necessarily extrapolate, what protein intake would lead to "nitrogen balance" where it seems their bodies would just be excreting whatever further protein you put in.
Statistics of "nitrogen balance" balance studies like this give us the figure that adults (without kidney issues, of course) should aim for 0.8 g protein ingested per kg bodyweight per day *for that is the value at which 97.5% --- that is, the mean plus 2 std deviations, one sided --- of the population reaches or passes 'nitrogen balance'*
Now, there's a bunch of methodological caveats about this... but the big thing is these large studies with their meticulously controlled diet intake of protein for a few days are run with the subjects largely being sedentary. It's not being done in the context of seeing how they react if they were to engage in recommended levels of strenuous exercise for a couple months or things like that.
(Point 2) As such, to make a long story short... indeed one longer than I'm ready to investigate at this point, lemme just point you to this non-paywalled paper...
<b>Protein “requirements” beyond the RDA: implications for optimizing health</b>
Stuart M. Phillips, Stéphanie Chevalier, and Heather J. Leidy
<i>Applied Physiology, Nutrition, and Metabolism</i>
9 February 2016
https://doi.org/10.1139/apnm-2015-0550
... and lemme explicitly quote its "Conclusions" and "Take-home points" here, **which should be seen to supercede the rules of thumb I have in my original post in this thread.**
<blockquote>
<b>Conclusion</b>
Substantial evidence indicates that protein intakes higher than the current RDA can be an important strategy to help promote healthy aging, weight management, and athletic performance. Protein quality, per-meal dose, and timing are also important considerations in practice. <b><i>Current evidence suggests that intakes of high-quality protein in the range of 1.2–1.6 g/(kg·day) is a more ideal target to achieve optimal health outcomes in adults.</i></b>
<b>Take-home points</b>
• Because of anabolic resistance, sedentary lifestyles, and common illnesses, older adults need higher protein intakes (≥1.2 g/(kg·day)) to help prevent age-related sarcopenia.
• Including a high-quality protein source at breakfast, the meal generally containing the least protein, is a simple and pragmatic approach to increase intakes in older adults, and has also been shown to reduce unhealthy snacking behaviour in younger individuals.
• The consumption of higher protein diets (∼1.2–1.6 g/(kg·day)), including ∼30 g protein per eating occasion, improves appetite control, satiety, and weight management.
• Athletes appear to benefit from protein intakes as much as 2× the RDA, with a per-meal dose of about 0.4 g/(kg·meal) consumed 3 to 4 times per day. Meal planning should be centred around postexercise protein provision to amplify the protein synthetic response .
• High-quality protein from animal-based sources (e.g., milk, meat, poultry, and eggs) provide a concentrated source of essential amino acids, including leucine, to maximize muscle protein synthesis, with relatively few calories compared with plant-based protein sources.
</blockquote>
"minimizing long term health damage from what's frankly a disproportionately body-dysmorphia-motivated sport"
Could you elaborate on this. Are you suggesting long term health damage is something non-professional, natural lifters should be concerned about? Thanks.
Short answer: No. I'm pretty darn sure that lifting weights, even quite seriously, is a big net plus for most people healthwise long-term if they're not using PEDs. [On that note, not to tempt people with the notion that, done right, the only side effect of PEDs is AWESOMENESS (a la that Simpsons episode when Marge gets into bodybuilding), but I think it's worth noticing that "Dr. Mike's" YouTubes on his Renaissance Periodization YouTube channel include many that are basically how to use PEDs so as to minimize both the short- and long-term downsides.]
Longer answer: Well, when I start figuring out what are --- and then reading! --- the papers that are the main evidence for the claims in my main post, I'll be sure to look at whether what seems to me to be a rising concern that people who get seriously into bodybuilding disproportionately have or develop body dysmorphia issues. On a "lighter" note (what a pun!) about mental health burdens of bodybuilding-style training, I gotta say that the many years where I exclusively did a certain popular sort of bodybuilding training --- that is, do quite a few sets per body part; do reps slowly, especially in the eccentric aka negative half of the rep, say 2 seconds concentric and 4 seconds eccentric; do full range of motion; and generally just lift weights with the ethos that "you got maximize all those little 'microtears' in the muscle, bro, to maximize muscle growth, so really bask in the sweet, sweet soreness created by accentuating load when the muscle is maximally stretched"... well, it contributed to a certain baseline misery of muscle soreness for me that didn't help my already-not-very-sunny baseline demeanor. I've been notably happier when I moved to classic strength-focused training (largely 5 or less reps per set, concentric phase as fast as can be controlled, eccentric phrase at most 1-2 seconds moreover with an eye to changing direction into the concentric as-fast-as-possible) for I've had a LOT less chronic muscle soreness.
>Thus, if 1.0g per kg bodyweight seems the asymptote of utility to competitive natural bodybuilders
Do you mean 1g/ lb bodyweight? That's what you stated above was the asymptote.
Yes, indeed. 1g protein/day *per pound* bodyweight is supposedly the most that even competitive natural bodybuilders need for their muscular hypertrophy needs. I'll add an erratum above. Thanks.
P.S. I knew I shouldn't mix kg and lbs since mixing metric and English units makes mixups likely... just like NASA expensively demonstrated in 1999: http://www.cnn.com/TECH/space/9909/30/mars.metric.02/
You are too kind! Thanks for this! You put a lot of effort into my question!
Where I am coming from is I'm a thin but healthy 81 year old but I have some difficulty having enough appetite for 1gm/kg and wondering if I should continue the effort or slack off. :) Sounds as if I should continue.
When I start looking for the evidence over the next 24-48 hours for the rules-of-thumb I quoted in my main reply in this thread, and especially what (if any) are the plausible quantitative ranges for marginal benefit as one goes up in daily protein consumption, I'll be sure to start with what motivated the USDA or other relevant government agencies to suggest relatively recently IIRC that the "recommended daily allowance" of protein should move from 0.5g / kg bodyweight / day to 0.8g.
I mean, I'm not a medical doctor... indeed <cough> I'm not even a PhD, leaving MIT all-but-dissertation... not that I haven't had some career in quantum computation nonetheless... but I digress... not ashamed I'm all-but-dissertation... not unduly fixated still on my difficulties-to-the-point-of-clinical-neuroses in regard to writing *formal, edited* scientific prose despite my not just ease but moreover genuine desire to type out reams-and-reams of scentific-ish prose stream-of-consciousness style on blogs such as this </cough>... but again, I digress.
Where was I? Right! Not an MD (and certainly not *your* MD... I know that almost assuredly no such disclaimer is needed, but I feel these interwebz need people to remain in the habit of issuing such disclaimers given <cough> recent brouhahas </cough> of not just lots of laypeople but many MDs being way too sure of themselves in their approach to <ahem> decision making under uncertainty during global pandemics caused by a novel respiratory virus </ahem>). Having issued that disclaimer, I contend it's worth injecting the following note of personal, intuitive common sense:
1) Though I hear that both hunger and, especially, thirst can get over-attenuated by age (that is, they may diminish to the point that they no longer guide one to eat enough and drink enough for good health)...
2) ... I'm largely inclined to say that --- unless you're explicitly trying gain muscle mass or, perhaps, stave off what feels like unduly rapid loss of muscle mass or anything like that --- than one is perfectly within rights to avoid feeling like you're force-feeding yourself in order to eat more protein. I mean, the present RDA of 0.8g per kg bodyweight per day is notably higher than the 0.5g I'm pretty sure reigned for decades. So, if you're pretty happy with the amount of muscle you have for your age and your strength levels and you've been averaging 1.0-1.2g per kg bodyweight per day but it's feeling unpleasant to eat that much, my educated-layperson's opinion is trying reducing to 0.8g per kg bodyweight per day for a month or two is a perfectly justifiable thing to try.
But I'll try to have a more "evidence-based medicine" answer to you (though again, not an MD... and <sad> not even officially a PhD </sad>) within 24-48 hours. ;)
This seems very sensible. Thank you. You really don't need to do more unless its now turned into your quest to track down the changed recommendation. :)
I haven't looked up studies, but I understand that high protein consumption puts stress on the kidneys, and can increase the risk of kidney stones.
The standard advice is that if on a high protein diet you should drink more water than usual.
I have no idea whether this is all borne out in fact.
I do a low-carb diet (health reasons), which ends up on the high-protein end, and can confirm that my kidneys low-grade hate it and I'm very prone to kidney stones. Drinking a lot helps - my strategy is that whenever I get up to refill my water glass, I drink one or two glasses right there in the kitchen, then only go back to where I was with my glass. I think I total to somewhere between three and four litres of liquid water a day (i.e. on top of any water that happens to be in my food) and that seems to keep the kidney stones away. The usual tips about avoiding kidney stones also apply - be careful with any vitamin D supplement usage, look out for other foods that might trigger them (e.g. spinach), etc.
Apart from that being too low for various demographic groups?
OH? I was wondering about the other direction, that it might be too high. But whihcever way, it seems it ought to depend on total caloric intake, activity levels and who knows what else?
As far as I know the composition of the essential amino acids in your protein can make a big difference in addition to the factors you named. I personally eat a lot less than 1g per kg, but I also can't move much because of an illness and don't digest high amounts of protein well.
It's been a while since I looked into this, but IIRC amino acid composition is very important if your protein intake is low, but less important if your protein intake is high. (Unfortunately I don't recall what was considered as low/high in those studies.)
Helpful. :) Thanks
As for moral decline, I suggest there has been some since COVID. In DC I adduce: more fast/bad driving, impatient honking, faulty or deliberately noisy mufflers, Metro fare evasion, carjacking, more murders, etc.
Is that "moral decline" or the already immoral people getting away with a lot more, since they are being arrested less? Steve Sailer notes that massive increase in homicides during COVID, was primarily an increase among Blacks, and that the concomitant increase in car accident fatalities was also primarily among Blacks. And that the spike occurred during the George Floyd protests, (rather than earlier when lockdowns began).
He suggests that the rise of anti-social behaviors was a result of depolicing, especially in Black areas - essentially a nationwide Ferguson effect.
Scott Alexander previously noted the evidence that the homicide spike was due to depolicing here: https://astralcodexten.substack.com/p/what-caused-the-2020-homicide-spike.
That could be true but I tried to give a range of anti-social behaviors. Impatient honking can hardly be the result of de-policing. :)
Maybe, but there's less data on the prevalence of honking so we have to take your word for it.
What I found during covid was that I got really pleasantly accustomed to the lack of traffic during the (extensive) lockdowns, and that it was very annoying when traffic became a thing again.
And the cheap flights! :)
I don't suppose BSP9000 is here as well? I'd be interested in judging and could undercut the people whose prices I can see there (being a NEET means I have a lot of time; I'd definitely be willing at $20/hour USD) but while I think I'm unusually honest I'm not exactly a celebrity so I'm not sure I have a *reputation* for honesty (my high intelligence is easily provable, though).
I'd say I'm pretty close to neutral on this issue; I went around Wikipedia back in 2020 saying that "it was a lab leak" shouldn't be listed under "misinformation" since it wasn't known-false, but I don't think that constitutes being super-biased against one side or the other (if one of the sides was "deliberate bioweapon release because reasons" I'd start out with a pretty strong prior against, but that doesn't seem to be the case). Hard to put numbers on it since I haven't really looked into it recently, but AIUI that's ideal for this position.
My ability to write long coherent monologues is patchy, but I should at least be able to write a list of points and which side I believe/why on each.
Email me (same username at gmail) if interested. Note that I'm Australian and sleep a lot, so there may or may not be timezone issues.
That's my reddit account and I do comment here, occasionally.
But I only just read this, and we're already well on the way to finding 2 people.
Also, an Australian judge is probably a dealbreaker because I'm in the US and Saar is in Israel, so any hours for this would be really awful for you.
Okay.
> I'm not exactly a celebrity so I'm not sure I have a *reputation* for honesty
I agree this is probably what prevents you from being selected.
I mean, like, there are people who know I'm honest. I got an official Sword of Damocles on a webforum (Sufficient Velocity) because they didn't like how open I was about the various bad shit and not-bad-but-illegal shit I've done over the course of my life. But I'm not sure how legible that is to a random Rationalist who doesn't know the people involved and doesn't want to just inhale my entire internet history. References who aren't previously known to the person looking are trivial to fabricate.
There's a tension between demonstrating non-Jewish influence on Early Christianity and demonstrating that it was a myth. The text of the New Testament is very explicit on fundamental Jewish continuity. If it was made up, what's all that about?
The Immortality Key seeks to do both. In that book Muraresku argues that Christianity is a continuation of the Mediterranean mystery cults such as the Eleusinian Mysteries. Accepting that premise I argue the authors were:
1) a group of Jews that had deeper issues with the Jewish Authorities than the Romans
2) who believed they had the ultimate truth and wanted to share it with the world.
This conflicts with Muraresku's treatment of Christianity, which emphasizes discontinuity with Jewish tradition. This isn't just splitting hairs about how much the syncretism was Hellenistic vs Jewish, it informs the nature of his posited Religion with No Name.
In the ACX tradition of too-long essays I expanded that idea here: https://www.vectorsofmind.com/p/the-immortality-key-forgets-that
Regarding the COVID-19 debate, I can suggest two judges: GPT-4 and Thomas Bayes. I'm being half serious.
I spent several hours over the course of a few weeks trying to get ChatGPT to perform a serious Bayesian analysis of the lab leak hypothesis. The results were very informative on more than one level, and at times (to me, at least) hilarious.
YMMV, but off the top of my head, here are the rough conclusions I drew:
- ChatGPT is very strongly biased against making any statements in favor of the lab leak hypothesis
- It's not good at math, but it eventually does a decent job at Bayesian reasoning if you're willing to go to the trouble of correcting it several times.
- Never ask it to name actual scientific papers; it will hallucinate them just about every time.
I never managed to get it to string together the posterior probabilities of several tests, but when I asked it to summarize the posteriors of those individual threads of conversation... judge for yourselves:
Me: Again, this is a very poor summary of the bayesian analysis we have conducted so far. Summarize the actual bayesian statistics using percentage likelihoods of each question in our conversation. Do not include subjective opinions; only percentage likelihoods.
ChatGPT: I apologize for any confusion. To summarize the Bayesian analysis conducted in our conversation, here are the percentage likelihoods based on the information and assumptions discussed:
- Likelihood of an intermediate host species for SARS-CoV-2 based on animal testing: 0.332%
- Likelihood of seroconversion in stored human blood samples for SARS-CoV-2 prior to the pandemic: 0.0000120%
- Likelihood of all 24,000 stored blood samples testing negative for SARS-CoV-2 antibodies given the existence of an intermediate host: 0.004%
These likelihoods were calculated based on specific assumptions, data, and test accuracy estimates discussed during the conversation. However, it's important to note that these calculations may not capture the complete complexity of the situation, and further research and evidence are necessary to obtain more accurate estimates.
... overall, the conversation was long and wandering, but I found it pretty interesting. I (or someone) should really do it over again using GPT-4 instead of GPT-3.5.
I found a ChatGPT hack called JamesGPT which was supposed to be able to get it to output the probability of everything. IIRC it gave me a high probability that covid was natural. And also a high probability that it is a lab leak.
I wonder if it is directly suppressed from speculating on the lab leak hypothesis, or if it just knows that's the sort of naughty thing it's not supposed to think about?
Huh... actually a very interesting question, and I have no strong opinion on the answer. Using RLHF as they do for this sort of thing, either could be true. They could collect a grab-bag of individual politically sensitive topics and play whack-a-mole, or (given how powerful the base model is) they could come up with a heuristic for politically sensitive subject matter and condition the model to avoid it as a general rule... but that runs the risk of going overboard and being less generally useful. Dunno, but I suppose it's likely to become public knowledge sooner rather than later, as things seem to be going.
It's sort of interesting, but the policy significance of lab-lead vs "natural" does not seem very important. What part of the COVID response should have been different if we had know that the origin was one or the other?
If it was a lab leak, the response should have included any lab that was doing GoF research on viruses stopping. That wouldn't have helped with Covid but it might have prevented the next version.
If it was being transmitted by an animal, knowing that and what animal would have suggested some precautions wrt those animals.
Isn’t the most probable lab leak just from studying wild viruses, even independent of any gain of function research?
It’s obviously good to regulate gain of function research, and collection of sick animals, and sale of wild animals in public markets, regardless of which of the three was most relevant for this pandemic.
In general, I think lab leaks are mostly going to involve unmodified wild viruses, but the minority that come out of GoF research are more likely to become megadeath pandemics. In the specific case of COVID-19, the presence of a furin cleavage site in SARS CoV-2, the absence of such in any of its known natural relatives, and the presence of a research group across town saying "Hey, let's splice furin cleavage sites into some bat-coronaviruses we have lying around" suggests that if this was a lab leak, it was those guys and their GoF work.
Agreed that all three of the things you cite should probably be looked at more closely than they are, but we should probably look first at the one that was most likely responsible for the latest megadeath plague.
But furin cleavage sites *are* present in plenty of wild coronaviruses. We don't know many of the close natural relatives of this one, so we don't happen to know any that have a furin cleavage site. But the frequency of furin cleavage sites in other branches of the broader coronavirus family at least undercuts the force of this particular argument.
Other coronaviruses, yes, but AFIK never in the sarbecovirus lineage that includes all the SARS-like viruses and all possible progenitors of SARS CoV-2. If a feature that's only ever been seen in wild muskrats starts showing up in hamsters, and it's just down the street from the lab of the mad scientist who keeps trying to create a hybrid super-hamster, you might want to consider hypotheses beyond "the hamsters must be responding to the same evolutionary pressures as the muskrats".
I have to admit up front that I'm outside my wheelhouse on this, but I did spend a little time looking into this when preparing questions for ChatGPT.
As best I can tell, the consensus in the scientific literature and from ChatGPT seemed to be that a sizeable complex like the furin cleavage site could only have been passed over into SARS-COV if the pre-existing coronavirus with the furin site was living in the same host as the SARS virus that received it, and that there is currently no known organism that would have been host to both.
The conspicuous theoretical exception could be one of the many coronaviruses that the Wuhan lab database might have contained, which hasn't been made public. Apparently it's well-attested that they have records of many others that the outside world doesn't have on record, and they haven't shared much of that information.
That might be for obvious IP protection purposes, and completely non-suspicious. But it does raise the question of why they wouldn't have shared knowledge of a host species of a coronavirus with the furin site and a known SARS-COV-2 predecessor... it seems like there would be a very strong incentive to share that information if they had it, for obvious exculpatory purposes.
Seems like both of these assessments of policy implications are "normative" rather than "positive" counterfactual. Sure, the optimal policy difference might not have been all that different, but in realistic terms, the actual policy differences might have been extremely different, depending on who was writing the policies.
I think the strength of the "suppression of evidence" (if you'll forgive that term for a moment, I'll attempt to justify it) is itself pretty strong evidence that those pushing the message had an expectation that if the lab leak theory gained dominance, it would have led to significant policy differences... perhaps such as attempts at retribution against those who allowed or enabled it.
I claim that "suppression of evidence" is a legitimate description, because most talking heads across the political spectrum continue even now to claim that there isn't enough evidence to make a strong claim... the problem is that any scientist knows that negative evidence is still actual evidence.
Just to take one example (take with a small grain of salt; this first set of numbers came from ChatGPT, though I verified that they are in the right ballpark):
1. For SARS-CoV, 62 of 146 (42%) stored blood samples collected between May 2002 and February 2003 in Guangdong province, the epicenter of the SARS outbreak, were positive for SARS-CoV antibodies using an ELISA test.
2. For MERS, 15 of 110 (14%) stored blood samples collected in Saudi Arabia before the outbreak were positive for MERS-CoV antibodies using a western blot test.
Given those priors, the fact that (according to a study published in Nature) 42,000 samples were tested for for antibodies against COVID in human blood stored in the area before the outbreak, and not one of them showed antibodies, is very strong evidence that there was no process of natural seroconversion going on.
Some salt with that 42k number as well; trying to backtrack and verify source...
It seems to me that the non-negligible probability that it was a Lab leak gets us to the same policy. It is worth trying to determine, but the intensity of the interest just seems excessive.
I started writing up book reviews on my college alum slack, and it's gotten positive feedback so I started posting them to my website:
Blind Man's Bluff: The Untold Story of American Submarine Espionage
https://ahalbert.com/reviews/2023/07/01/blind_mans_bluff.html
Ok I think you do need a proof-read: there are typos, repeated sentences, some confusion about "he" (captains) and "she" (boats) and who was doing what....
That aside, it is so comprehensive it's more like a spark notes summary than a review. You hit pretty much most of the content, minus lots of details, but it leaves a lot less for the reader to get from reading the actual book.
The way the wiretap was sold out angers me so much, as it did when I first read about it.
Thanks for your feedback, I'll spend some time proofreading
I read that book a long time ago and liked it a lot. I'm still reading through your post, but somewhere you write "ocean floot" instead of "ocean floor".
Thanks for the correction, and thanks for reading!
This is interesting, please keep up the great work.
Thanks for the encouragment, I really enjoy sharing what I learn from reading.
Another recent one:
It's Our Turn to Eat: Corruption in Modern Kenya
https://ahalbert.com/reviews/2023/07/01/its_our_turn_to_eat.html
Since this is an open thread,
I wondering if anyone would be interested to read a newsletter that educates 'health" without the medical jargon.
I'm a doctor and feel like this would help people.
Will cover things like, "How does tylenol work? Why does it work for fevers but not for heatstroke?"
"How can cholesterol be good and bad at the same time?"
Things like these.
Would you be interested in it?
Yes, I just pre-emotively subscribed to your substack account to be notified if/when you start this.
Awesome, maybe by end of this week.
If you have any topic in mind that you would like to learn more in this field, I'm all ears.
Just spitballing, these could be interesting to me:
Nutrition: what do we actually know / is settled science regarding what’s healthy and what’s not healthy?
Raising healthy children
What to think about the ethics and advantages/disadvantages of giving known placebos?
Yes! Most enthusiastically!
I attended a lecture series (Wagner Free Institue of Science), on common drugs and their history/bio mechanism, and sometimes business. So, aspirin/nsaid, cholesterol, thalidomide, hallucinogens, rogain, and a few others.
Awesome! Working on the newsletter right away. Don't shy from giving me any pointers/tips for my first issue
Yes!
Awesome.
Yes, I would be interested in something like this!
Great. Thanks. If you've specific topics you want to read about, let me know
With regards to aging, is it optimal to be jacked, or thin? I’m working out a lot and have had to massively increase my caloric intake, and worry about the increase affecting health over the long term.
its a complicated topic and depends on what you mean by aging. Lots of people die or have significant declines in quality of life because of a lack of adequate muscle mass. Usually this takes the form a fall which can kill someone or lead to needing surgeries to fix broken bones and joints. Without adequate muscle mass, recovering from a broken him or knee or leg, becomes very difficult. More muscle mass before the accident makes recovery easier which is likely to maintain a higher quality of life.
In terms of the theoretical idea of aging, i dont know. My recommendation is that, for almost everyone, your problems are more likely to come from being took weak or too obese than from having too much muscle mass. If you are gaining weight I would make sure you aren't becoming overweight/gaining too much fat at the same time as muscle.
Yes, I’m trying my best, but if I do gain a bit of fat and then lose it, are there long term consequences?
I don't *think* so (assuming you aren't blowing up to like 300 plus pounds), but I am not a doctor. My favorite resource for these topics is the folks at Barbell Medicine, run by two doctors who are also accomplished power lifters so they have lots of relevant experience. They have a great podcast: https://soundcloud.com/user-344313169 not sure if there is an episode on the specific question you have, maybe this one: https://soundcloud.com/user-344313169/205-mixdown-1 called Training for Strength vs Training For Size.
FWIW my coach has referred me to this recently: https://www.worth.com/muscle-is-the-cornerstone-of-longevity/
"With regards to aging, is it optimal to be jacked, or thin? I’m working out a lot and have had to massively increase my caloric intake, and worry about the increase affecting health over the long term."
A random YouTube video I watched recently suggested that the following are positively correlated with living longer:
a) More muscle
b) More strength (not the same thing as more muscle, though clearly related)
c) Move VO2max
[NOTE that (a) and (b) can probably be taken to an extreme where more is worse ... that wouldn't necessarily show up in lots of regressions if the sample didn't have folks who took powerlifting/body-building seriously]
These all sound reasonable, so you might want to explore these. I'll note that there is a difference between "thin and with poor endurance/VO2max" and "thin and with lots of cardio capacity." There is also a difference between "thin" and "not fat."
I 'll also note that "optimal" for aging can mean several things. Do you just want to maximize your expected lifespan? Or is quality of life important, too?
I think it is known that caloric restriction extends life and slows aging
in mice?
I have no meaningful knowledge, but felt like mentioning it's harder to gain muscle as you get older, and just as easy to lose it, so going into elderhood with lots of muscle is a safer bet than going in without.
Depends on what choices you made earlier, including choosing your parents. I.e. be careful of the swimmers-body fallacy when thinking about how you personally should optimize your health practices.
But all else being equal (which it never is) calorie restriction increases lifespan.
My semi-educated bet would be against thin, at least if you are on the very skinny side. Severe diseases can make you lose weight, and you may be less resilient if you are too skinny. Mortality increases with underweight, though only moderately. (And it's hard to tell apart cause and effect).
Probably most worrisome health effects (especially cardiovascular ones) come from fat tissue, not from body weight. So building up muscles is probably good for your health. But overall, both thin and muscular are much better than fat.
Some caveats: if by "jacked" you mean the bodybuilder look with sixpack, that's a pretty extreme combination of muscles and low body fat, so that's probably not optimal. And using steroids is so bad for your health that it easily dominates any positive effect of muscles.
Be as jacked as Patrick Stewart. He’s actually fairly built, but nothing showy. All of which meant he didn’t visibly age for decades and looks great for 82.
I actually don’t know the literature but I imagine that at the very least reducing muscle loss has to be a good thing and could possibly help with bone and muscle pain in later age.
My non-expert advice would be that if you're going to do weight training in old age, concentrate on your core and leg strength. You're probably not going to be called upon to lift too many heavy boxes, but you want to maintain your mobility.
I think people should not shy away from building upper body strength anyway - and old people have to lift stuff.
Long Bets is a purpose built division of the Long Now organisation for moderating bets like that COVID origin one.
As a slight tangent, I'm always a little disappointed when I hear about bets where the proceeds are pledged to the charity of the winner's choice. The point of making a bet is that you have skin in the game. You will lose money if you're wrong and gain money if you're right.
A charity bet means you've spent money whether you win or lose the point. The visceral impact from skin in the game has to be significantly diminished.
Now, I'm all for charitable donation. But I'd rather see that happen separate from (and not as a pre-commitment before) the bet itself.
This.
I'm challenging Rootclaim to the debate. By the time this is done, it could easily end up being 6 months of effort spent researching this topic and coordinating the debate details.
There's no way I would have done this for free. It's already a questionable use of my time, compared to working on something else for a similar length.
I would definitely have been willing to do it as a long bet where I get the money, but I tried that first and couldn't get Saar to agree on terms.
And I definitely wouldn't do a long bet where we both lose $100,000 and some charity wins. Even if I were charitable at that level, I would just donate the money now instead of making the bet.
Great point. What's the value proposition for the individual donating/debating? They trade a 100% chance of giving the full value to the charity of their choice, versus some smaller chance of that same charity getting more, with the risk of that charity getting nothing. That's not a great value proposition.
The real value of the 'bet', when tied to a charitable donation is in the signaling value of the dollar amount as an advertising tool. "I debated Y for $X dollars!"
If it's a long bet, you may well not be around when it's resolved, but your favorite charity may.
Also, people tend to discount future gains so strongly, that I'm not sure even the promise that your estate will benefit would put much additional weight on the direction. (Your estate sort of *is* a charity...just with very specific beneficiaries.)
Seems like a 'long bet' doesn't function like a bet so much as a preregistered prediction.
Whether the costs and benefits are passed on to charity or to heirs, the value of the betting framework seems equally reduced.
I just copy-pasted the link to paper's author's Substack that other people had posted in the comments before me, (almost) all of the credit should go to them, most likely Filippo : https://astralcodexten.substack.com/p/is-there-an-illusion-of-moral-decline/comment/17941783
Otherwise I agree that the Nature (!) paper should be able to stand by itself... or at the very least for a term as fraught/slippery/vague as this one should have linked to (several) other works that have studied its etymology (did it ?)
One way to cut through the moral haziness.
It's mostly about sex. Young people fucking more than before (for real) or sexual behaviours being more apparent (porn, gay pride, advertisement) means societal decay is going to bury us all.
The other element is "respect for your elders". Funnily enough, elders never think they're as respected as they should be...
(The great mass of) Conservatives aren't subtle...
There is something sad about reducing morality to "be obedient and sexually frustrated"...
Right, sex is a big part of it. While each individual sex act might be harmless, the normalisation of premarital sex has had two pretty terrible consequences:
1. In the lower classes, an increasing fraction of young children being brought up without both parents (particularly in certain communities)
2. In the middle and upper classes, below-replacement birth rates due to delayed family formation (no time to have three kids if you don't get married until age 35)
It seems to me that these little decisions are the sort of thing that moral decline is made of. Every day you're faced with choices between doing the easy, selfish, pleasurable thing, or the more difficult and pro-social thing that leads to better outcomes in the end. The moral drift of the last fifty years (or of the first century BC in Rome) has been almost entirely in the direction of justifying the easy, selfish, pleasurable thing.
I'm skeptical on your second point - making people get married in their early twenties if they want to have sex in their early twenties, doesn't seem like it's going to change the "I can't afford to have kids until my career is established and I've bought a house" thing that has so many people waiting until their late 30s to have children. It just gives us a bunch of 20-something DINKs trying to thrive (by their own upper-middle-class standards).
I'm sure there's some people who put off having kids until their late 30s for economic reasons. I think there's also some who put off having kids until their late 30s because they don't decide to settle down until their early 30s.
But you're not making them settle down, you're just making them get married. Most likely to the fun-loving 20something spouse that best shares their not-settling-down-yet goals.
Maybe, but AFAIK there aren't and good examples from history of groups of people where it was common to get married early _and_ not have kids for 10 years. Is your prediction plausible? Yes. But I'd still put my money on getting married early resulting in more kids. It's historically correlated with it at the very least, and, in my limited experience of N=1, causal as well.
There also aren't many examples from history of groups of people who could physically manage to have PiV sex at all and not have kids for ten years. History is not a useful guide here.
Do people exist for society or does society exist for the people?
Both. If people become unable to sacrifice for society, the society dies, and that's very bad.
There's also something else: it's extremely important to have principles that are capable of overriding your desires. It makes you be of service to others, and it greatly enhances your capacity to act (because you don't let things like sloth or doubt stop you).
I though people were worried about not enough sex; symptom of disconnectedness due to cell phones, etc. ?
Some people are, but the one's who are don't call that "moral decay".
I would also say that if you ask me and my parents what I mean about moral decline, we would literally say the decrease in religion, which is where our morality comes from. I, but not my parents, accept that you can be moral without religion, but my personal morality is tied so much with Christianity, that if you polled me on the question, that is what I would base my answer on.
Right. But religion is a tad vague.
I doubt that your parents/yourself are really concerned about the decline in Christian charity or Christian humility... I bet that, if you scratch, religion (for most) really means sexual propriety/respect for your elders' way of life.
That depends strongly on which groups you look at. For some it means (approx.) "submission to traditional myth of origin". The ones most "devoted" to the "word of God" are very selective about which parts they remember, though.
I dunno, let's look at the least religious countries ( https://en.wikipedia.org/wiki/List_of_countries_by_irreligion ) and look at their history over the last century or so:
1. Czech Republic (not very peaceful over the last century but we can largely blame foreign influence for that)
2. North Korea (not at all peaceful)
3. Estonia (again I will mostly blame its neighbours for the lack of peace here)
4. Japan (invaded all its neighbours)
5. China (two civil wars, multiple neighbour-invasions and a couple of hundred million dead in various genocides, still threatening to invade its neighbours)
6. South Korea (see North Korea)
7. Latvia (see Estonia)
8-10: Netherlands, Uruguay, New Zealand: finally some peaceful countries
do you have a source? i had thought sex was in decline?
Relative to ten years ago, young people are less slutty. Compared to sixty years ago they're more slutty.
this seems relevant https://www.bustle.com/p/the-average-age-people-lose-their-virginity-across-different-generations-8015518
and does support the claim. that's really all i was asking for, sheesh
Pretty low quality source. Here is a better source: https://yrbs-explorer.services.cdc.gov/#/ The CDC does a bi-annual survey of americans under 18 on "risky" behaviors like sex and drugs, you can explore the data at that link. The most recent survey data is 2021 but that is skewed by covid (hard to have sex when you can't be in the same room). So I'll use 2019 below. 1991 is the oldest data they have.
Highlights:
High School Students Who Ever Had Sexual Intercourse:
1991: 54%
2019: 38%
https://yrbs-explorer.services.cdc.gov/#/graphs?questionCode=H57&topicCode=C04&location=XX&year=2021
High School Students Who Had Sexual Intercourse For The First Time Before Age 13 Years:
1991: 10%
2019: 3%
https://yrbs-explorer.services.cdc.gov/#/graphs?questionCode=H58&topicCode=C04&location=XX&year=2021
High School Students Who Had Sexual Intercourse With Four Or More Persons:
1991: 18.7%
2019: 8.6%
https://yrbs-explorer.services.cdc.gov/#/graphs?questionCode=H59&topicCode=C04&location=XX&year=2021
High School Students Who Were Currently Sexually Active:
1991: 37.5%
2019: 27.4% (this is interesting because its pretty much flat until 2015 when it drops by 4% points from 2013)
https://yrbs-explorer.services.cdc.gov/#/graphs?questionCode=H60&topicCode=C04&location=XX&year=2021
So at least in the US it seems people under 18 are having less sex and having it at older ages.
That's why I also added the perceived part - the porn etc.
I do not know if we/the youngsters these days are doing it "more" than in the 40s (I imagine so, though. It feels like marrying a virgin was a distinct possibility back then, not so much today but obviously that's linked to marriageable age etc) but one thing that is absolutely indisputable is that the culture is more comfortable and open with sex/sexuality (even if it's still far from ideal)
Young people today are having less sex, partly because they are getting married at older ages and marriage is a convenient way to always have a sexual partner. Arranging a ton of hookups is logistically challenging.
When you say "far from ideal", you are pointing to your personal moral code, and everybody else has to guess what you mean. (OK, parts of it are a pretty reasonable guess.)
But this is the problem with claims of "moral decline". (Just about) nobody explicitly defines just what observables they're talking about. Does it include farting in an elevator? I'd guess that you wouldn't get agreement on that, and only *some* would hedge. What about running a coal mine? Is that moral or not? How about supporting a foreign war? Refusing to bake a cake for someone? It's a huge amorphous blob, and different people pick different parts of it to attend to.
Fair enough but, as stated, my sense is that it's primarily about sexual license (perception thereof) and "respect for your elders".
As to my ideal sexual milieu, it's the standard liberal view - everyone does as they please, as long as it's done with informed consent from all parties involved. They are tons of edge cases and I might come down differently from the majority on many of them but, broadly speaking, that'd be my uncontroversial take.
Whole I support that in the hypothetical, in reality sex leads to babies, and the people expect me, a taxpayer, to help support the baby that they were unprepared to have. While I appreciate that babies should get enough support to live happy childhoods, I'm not thrilled about the chain of events that leads to tax-subsidized child support.
so I guess that I lean towards if you have informed consent and effective contraceptives, do what you want. Otherwise I reserve the right to be judgy
original post says <quote>Young people fucking more than before</quote>
so if you <quote>do not know if we/the youngsters these days are doing it "more"</quote>, maybe change that part?
Can I use an "or" to indicate either/both? For example, the decline in sexual activity seems to have reversed (according to some research I saw on Twitter) and the peaks observed in the 80s and 90s might have been linked to lead poisoning i.e. maybe we're just returning to a trendline?
Bottom line, I used an "or" because I wasn't sure and wanted to cover both eventualities.
I would definitely dispute that ‘the culture’ (I guess you mean Western English speakers?) is more comfortable with sex. Not only do we appear to be having less of it, it appears to me that we’re fixated on practices, and obviously unhealthy and bizarre fetishistic practices have proliferated and become common to the point that it is socially unacceptable to point out that they’re unhealthy or abusive whether to others or the self.
To me it looks like the median person is much more uncomfortable with sex now—they can talk about it in general, but they’re afraid of having it, they’re afraid of flirting, they’re afraid of the intimacy and remove it from the equation to be replaced by fetish behavior, and they have a much harder time maintaining sexual relationships in the long term.
In short, you may not agree that any of this signals discomfort, and you may believe that lots of talk about sexual practices equates to ‘openness,’ but I don’t think you can say this is beyond dispute. It’s definitely disputed.
I don't think I used the term "more comfortable" or "openness" in the opening comment. I used the term "more apparent".
That, I don't think, can be disputed. Just the existence of porn and the prevalence of raunchier mainstream ads/movies/cultural artifacts seem impossible to deny (Which 1940s singer perform in underwear like Miley Cyrus did)? You may call these pornification of society a fetish or unhealthy but you are not denying it took place.
And, to religious people, that has to look like moral decay...
“one thing that is absolutely indisputable is that the culture is more comfortable and open with sex/sexuality”
That’s the sentence I’m responding to.
As far as porn being more “sexually open,” doesn’t really count in my view. Pornography, private or public, is a specific kind of sexual performance and entertainment and doesn’t really represent what happens during sex any more than The Office faithfully represents all white-collar work.
Fair enough, I did write that subsequently. A bit sloppy as I cannot prove it. But, to me, when you go from American Gothic (the 1930 painting) to Marilyn Monroe flowing skirt to Instagram influencers in bikinis, it seems society is more open to /comfortable with sex/sexuality, even if you can argue that everyday practices haven't changed or haven't changed for the good...
Not only that, but porn is usually a substitute for actual sex. If people are watching more porn, and more extreme porn, that's probably a direct result of a decline in actual sex-having.
During times when I've been in a long-term relationship, my porn consumption has been approximately zero, because that need was being met elsewhere.
1940s vs Miley Cyrus is an impoverished data set, insufficient to describe a possible cycle. A few years earlier you had Josephine Baker and pre-Hayes Code cinema.
And how do you think pre-code movies compare to more recent fares in the sexual imagery department?
Furthermore, the Hays code was imposed and enforced. How likely do you think it is we get an updated version? I would put the odds at around 0% within the next 5-10 years.
I think it’s becoming relatively easier to find male virgins. Maybe because of the “double standard” they don’t count.
Fair point but, yes, I don't think male virginity was ever considered one of the moral pillar supporting the whole of society. Female virginity, otoh...
There seem to be quite a few "read my blog"-type posts here, which I thought were discouraged in Open Threads. Has the policy changed?
I just found a clever hack -- if you write less than three articles per year, you can advertise each of them!
The official rule is that you may do this twice a year outside of Classified threads, and the second one should be sort of subtle (like "I just wrote a great article on Topic, interested if you have feedback")
I don't always notice when people violate this, but I notice eventually when people do it every thread and try to crack down. If you see people abusing this, please report it and put the number of times you've seen them do this in the report comment field.
"The official rule is that you may do this twice a year outside of Classified threads, and the second one should be sort of subtle (like 'I just wrote a great article on Topic, interested if you have feedback')"
Is this "twice a year" at all, or twice a year without context?
More specifically, if there is some thread and I have a (possibly old) post on the subject is posting a link to the write-up discouraged?
Is there a difference between A) someone posting a link for self promotion (look at my blog) versus B) someone posting a link to a response to an ACX post? They seem to me like they're functionally different. One is for self promotion and could pollute the comment section if there is a lot of it. The other seems like it could extend discussion where charts/graphs would improve the debate. Of course I’m not unbiased here, since I’ve posted B in the past.
I would say there is nothing objectionable about B, as long as the link is relevant and there is at least a sentence or two in the comment to let people decide whether the link is worth clicking.
It's always been sorta tolerated, and you can report people whom you feel abuse this lenience too much, but you're right in that there's a lot of it today. It might be good to have a "read my blog" nested comment on these open threads but I worry that's only going to encourage people.
I permanently solved this problem for myself by embracing my identity as a 'reply guy'. I wish I could disable the part of Substack that apparently thinks that I should be starting a blog at any minute.
> So was Abraham more or less “kind” than we are? I think a Bronze Age Hebrew would say kinder (because hospitality is most important, but what you do with slaves is your own business) and most moderns would say less kind (because feeding anyone who comes to your door is so crazy you don’t even really get credit for it, but keeping slaves is monstrous).
It's worth noting that we consider it monstrous today because of relevant experience with monstrous slaveowners in the American South, a system that has very little to do with the Biblical words translated as "slave." Virtually every aspect of Southern slavery that makes it monstrous and evil, (including what most people today consider the definitive characteristic of slavery: owning a person as chattel,) was specifically forbidden by Biblical law. While not an *exact* match, the concept would be much better rendered into modern English as "employee."
I think it's closer to serf. They didn't have the right to quit.
Perhaps "indentured labourer"?
> Virtually every aspect of Southern slavery that makes it monstrous and evil, (including what most people today consider the definitive characteristic of slavery: owning a person as chattel,) was specifically forbidden by Biblical law.
Where is the passage prohibiting owning a person as chattel? I found one prohibiting owning an Israelite but allowing owning a foreigner. And it specifies *buying* these people, and leaving them to your children as an inheritance.
Leviticus 25: "44 And as for thy bondmen, and thy bondmaids, whom thou mayest have: of the nations that are round about you, of them shall ye buy bondmen and bondmaids. 45 Moreover of the children of the strangers that do sojourn among you, of them may ye buy, and of their families that are with you, which they have begotten in your land; and they may be your possession. 46 And ye may make them an inheritance for your children after you, to hold for a possession: of them may ye take your bondmen for ever; but over your brethren the children of Israel ye shall not rule, one over another, with rigour."
Another passage, in Deuteronomy 21, says that if you take a war captive, and marry her, you may not then sell her. This implies that if you do not marry her, you may indeed sell her.
"10 When thou goest forth to battle against thine enemies, and the LORD thy God delivereth them into thy hands, and thou carriest them away captive, 11 and seest among the captives a woman of goodly form, and thou hast a desire unto her, and wouldest take her to thee to wife;
12 then thou shalt bring her home to thy house; and she shall shave her head, and pare her nails; 13 and she shall put the raiment of her captivity from off her, and shall remain in thy house, and bewail her father and her mother a full month; and after that thou mayest go in unto her, and be her husband, and she shall be thy wife. 14 And it shall be, if thou have no delight in her, then thou shalt let her go whither she will; but thou shalt not sell her at all for money, thou shalt not deal with her as a slave, because thou hast humbled her."
> Where is the passage prohibiting owning a person as chattel?
The clearest one is found in Deuteronomy 15, where it states that a slave shall not serve a master longer than six years, and must be set free the seventh, not simply thrown out but provided for with a generous severance package, (to inject a bit of modern terminology,) unless they decide of their own free will that they'd prefer to stick around for life. (Exodus 21, covering this same rule, adds that the freely-chosen servant must be taken to "the judges" to solemnize this status, presumably to prevent abuse.)
This casts the inheritance rule you mentioned in a different light: If someone is working for you on a six-year contract, and you die before the six years are up, your heir in the family business has a right to take over the contract.
Out of curiosity I checked this out and Deuteronomy 15 is about Hebrew slaves, in the context of a more general seven year expiration for debts owed by other Hebrews where foreigners are explicitly excluded. So if you're right that this is the clearest passage that's bad news for your point.
I would just like to point out that I, at the very least, believe that owning slaves is monstrous for reasons that have nothing to do with American chattel slavery, and that all forms is slavery are monstrous.
Although I'm trying to understand what distinction you are drawing here:
>owning a person as chattel
Being owned is literally the (modern) definition of slavery. I'm not sure how one can be a slave and yet not be owned. Are you arguing that the translation is bad and we actually wouldn't consider them slaves?
If you were a slave but your master wasn't allowed to sell you to somebody else, that would be non-chattel slavery.
I suppose a lot depends whether you count serfdom as slavery or not. But that was common when the concept of 'ownership' of things like land was also much more complex.
Either way, it's monstrous for a private entity to have access to non-free labour, whatever other rights or obligations that's bundled with.
> Being owned is literally the (modern) definition of slavery.
Agreed.
> Are you arguing that the translation is bad and we actually wouldn't consider them slaves?
Yes, asterisk. It's not that "the translation is bad" per se; it's that the translation is centuries old and the meaning of the word has shifted since the translation was made. (And even more modern Bible translations tend to rely on older ones more than you might think. They'll get rid of obviously archaic terms like thee and thou, but keep around a lot of words that are still in use today even if their meanings don't quite line up. It should not come as any surprise to anyone that the field of scriptural translation proves to be a rather conservative one!)
The modern notion of "employee" (and particularly of "career employee") more or less sprang into existence as a result of the Industrial Revolution. Before then, most people worked in the family business, which remained a small family enterprise (usually farming) unless you got really lucky and struck it rich. The ancient version of "slavery" was a (somewhat) compassionate practice, where a wealthy individual would take on poor people whose families couldn't afford to raise and provide for them, giving them food, shelter, and wages in return for their service, for a given length of time, after which they were free to try to seek their own fortunes, or remain with their old master. (Modern ideas like "at-will employment" simply didn't apply to societies without an abundance of employers constantly looking for people to hire.)
If slavery was even somewhat compassionate, why does Leviticus 25:46 prohibit the enslavement of fellow Israelites?
Maybe. You are clearly speaking about a very culturally specific form of slavery. The Athenian child slaves who died in the silver mines would not have considered it other than horrible.
OTOH, among some of the early Caliphate states, a slave would frequently rise to become the "prime minister". It's VERY culture specific. This pretty much guarantees that there's no one word that will cover centuries of use, and suggests that there may not be ANY modern equivalent to any of them. So slave is probably as good a word as any. And it's worth remembering that the Law says what it says, but people tend to do what they can get away with. And an authoritarian dominant figure living on a rural property before the telephone can get away with a lot.
Why are all forms of slavery inherently monstrous?
What if someone owned someone else but gave them complete freedom to do as they wished? (as if they were a free man). The only exception is that the master taxes all earnings made by their slave by 20% and uses that money to fund the educational, profesional and physical development of that slave and all his other slaves. (for example, he would pay for their college education to increase future earning potential).
Is that still "monstrous"? If so, how is this relationship significantly worse than the relation between a man and his government?
You're making a good argument for the relation between a man and his government being monstrous 😉
That's because it's basically the libertarian Robert Nozick's "The tale of the slave" argument but in reverse
Slavery is when you are compelled to do specific forms of labor. When you are taxed, you are not compelled to do specific forms of labor. You fail to pay taxes and the government starts garnishing your wages - there's no job requirement here. In this hypothetical, the slave owner is just not exercising his power as a slave owner beyond the degree to which a bank is exercising its power over debtors in default.
You might as well ask, "what if someone owned someone else but gave them complete freedom to do as they wished?" Well then they would be the one good slave owner, as they are basically letting their slaves be free. It's not wrong to buy a slave to then immediately manumit them, after all.
We are dangerously close to a semantics debate, of course if I define slavery as only what happened in the American South it is monstrous, but that definition would leave out most slaves that existed throughout history.
I simply used the definition provided by the person I responded to (and Wikipedia, Britannica, the ancient Romans and Greeks and every other source I've seen): Ownership of people as property.
For an example of a slave that doesn't fit your definition, see the Greco-Roman philosopher Epictetus who studied philosophy while still being owned by another person.
When evaluating historical forms of slavery, you have to compare the conditions of slaves to the comparable conditions of an impoverished free man living in the same society. Obviously being a slave in ancient Rome sucked, but being poor in Rome sucked in general.
Slaves in the American south had significantly worse lives than impoverished free men living in the same society, mainly due to the especially racist nature of it. (which btw, also existed in Sparta)
However, Mamluk and Janissary (and other) slaves in the Muslim world (in certain periods) didn't live as well as middle or upper class people in their societies, but they probably had significantly better lives than most poor free men.
Does the master also pay 20%?
Can the slave himself become the master by convincing other slaves to vote him in charge? At which point the old master goes back to being another slave?
No, this is still slavery. The master is the master, no matter how benevolent he may be.
As for paying, he can fund his slaves from his own capital as much as he sees fit according to his own interest in their professional development. (A computer engineer will give him a much higher lifetime return on investment than a janitor.) There is the possible exception that if in this weird neo-slavery society that exists in this hypothetical there are governmental regulations forcing him to fund his slaves to a certain minimal extent (think, minimum wage laws) then he would have to comply with them.
In that case, to answer your last question, I think there’s a significant difference between the relationship you describe, which is one of a (benevolent?) autocrat and subject, and the relationship between a man and his government, at least in a representative democracy, in that the latter has the potential both to place constraints (constitutions, magma carats, etc) upon the decision maker, force his decision maker to change, or even supplant him personally and relegate him back to the commons.
Acknowledging that various individuals place different values on that kind of agency, I personally think that difference is big enough to make the former “significantly worse” than the latter, and I expect most people (at least those raised in democracies and accustomed to having that kind of control over their authorities) would agree.
[edit] Also, more objectively speaking, there’s the capacity to replace failing leaders by means other than force, which renders existence under a modern government very different from and much preferable to they hypothetical “benevolent master” system described.
They'd be an autocrat
What if the master lets their slaves vote on how their taxed money gets spent? Or at least let them elect representatives that direct his decision? At which point of "autocracy" does this type of slavery (remember, he still owns all of these people) become monstrous?
How do you define "owns"?
Because if ownership means complete right to do whatever you want with your alleged property, then the only thing stopping this system from being monstrous is the master's goodwill, which is not good enough.
It IS monstrous. And it isn't.
I specified that Abraham had a child with his female slave, then threw them out into the desert to die. This isn't legal to do with ordinary employees, and I think undermines your attempt to make the equivalence.
> Abraham had a child with his female slave
Not exactly. There's a ton of nuance and mismatched cultural expectations being elided here. In your article you speak of how we find ancient customs of the sacred duty of hospitality strange today. Well, their customs regarding the sacred duty of reproduction were just as serious to them.
First off, Hagar was *Sarah's* servant, not Abraham's. When Sarah suffered long-running problems with infertility, she arranged for Hagar to give Abraham a child instead. This definitely seems odd to our modern sensibilities, but it wasn't a particularly unusual practice in ancient times, and it wasn't just the women who had unusual (by today's standards) burdens placed upon them in the name of the duty to "multiply and replenish the earth." The law of levirate marriage says that if your brother married a wife and then died childless, you were obligated to marry her and your firstborn child together would be officially your brother's, to continue his line.
> then threw them out into the desert to die
Uhh... yeah. This part never actually happened, for two reasons. First, well before the point where Abraham dismissed Hagar, Abraham had received a promise from God that Ishmael would grow up and become a mighty and prosperous man. So he knew he wasn't sending them to their deaths. (And while one could claim that the only evidence we have of this alleged divine revelation comes from the Genesis account, this is also our only source for the Hagar narrative at all. If you're going to discuss Abraham's behavior you have to take it in its full context.)
Second, these were nomadic herdsmen. They didn't live in "the desert" because that wouldn't provide them adequate grazing land. (The desertification of the Middle East is a more recent phenomenon.) He gave them food and water and said they had to leave, because Ishmael was "mocking" Isaac to the point of rousing fear in Sarah. (Given the typical Hebrew propensity for understatement, it's likely that this "mocking" refers to actions that were endangering his younger half-brother.) While it's true that Hagar showed a certain flair for the dramatic, proclaiming that they had been left to die of thirst, this idea was immediately shut down by the appearance of an angel, who (rather exasperatedly, one would imagine) told her "look, there's a well of water *right over there.*" The Genesis narrative gives us no reason to believe that 1) they were intentionally sent out to die, or 2) that they were particularly in danger of dying at all.
> This isn't legal to do with ordinary employees
As I said, the concepts are not a perfect match. But it's still a much closer comparison than the modern-day, Southern-influenced image of slavery.
The Bible states that this was in "the Desert of Beersheeba".
I think the verse where she is saying she is about to die of thirst and the text says "Then God opened her eyes and she saw a well of water" is implying that God miraculous created the water, or at least that she would not have found it without divine aid.
The Muslims go into this story in much more detail and say that "The story of the appearance of the well either involves the infant [Ishmael] scraping the ground with his feet and water springing out or God sending Gabriel who consequently opens up the well using a variety of methods depending on the narration."
>The desertification of the Middle East is a more recent phenomenon.
I didn’t know this but it makes a lot of sense!
I can't find the passage in question, but I suspect it's a translation issue. The English word "desert" used to mean "wilderness", so a translation into archaic English would be misleading to modern readers. (That said, I am still skeptical of the claim that Biblical slaves were not really slaves.)
I get that “desert places” aren’t necessarily sandy Saharas. Still, it’s interesting to find out that the region was greener in the past. It does gel with the fact I do know that there used to be lions there but aren’t anymore. Human activity is the main driver in their extinction but it’s also hard to imagine lions thriving in a place as dry as modern Israel.
Blame it on the goats. The goats eat the seedling trees, so no adult trees grow up to replace the ones that die. This causes the local weather to get hotter and drier.
The passage in question is from Genesis 21:14: "וַתֵּ֣לֶךְ וַתֵּ֔תַע בְּמִדְבַּ֖ר בְּאֵ֥ר שָֽׁבַע" "and she went and wandered in the desert of Be'ar Shava". The meaning of Be'ar Shava is explained a couple verses later as the place where Abraham and Avimelech swear(Shava) an oath concerning wells (Be'ar).
And מדבר generally means wilderness or desert
https://www.studylight.org/lexicons/eng/hebrew/4057.html
As I said, if you're going to discuss the Abraham story as written in Genesis, you have to take the whole Genesis story as context. *Within the context of the story being criticized here,* "throwing them out into the desert to die" is not what happened.
Sorry, but no. We're talking about "moral decay", and the story of Abraham was held up as the story of a righteous man. Whether it actually happened is irrelevant. (Arguing that "on the basis of the story" they were sent out to die is valid. So is arguing that "on the basis of the story" they weren't.) The question here is "what is considered moral behavior", and this clearly indicates that sending your son by someone who wasn't your wife away from your protection was considered moral. (One can speculate about what the justifications mean, but they *are* justifications.)
It's important to remember that the question is not just "what did he do" but "why did he do it." The son in question was mistreating, and quite likely endangering, his other son with his behavior. As Leo Abstract pointed out in a different comment, Ishmael was not a helpless little child at this point either; he was old enough to be considered a man by the standards of people who had not yet invented the concept of adolescence.
Protecting a small, helpless child from abuse at the hands of someone much larger should count as moral behavior in *everyone's* book, no?
If Abraham had employees rather than slaves, his society had dire need of labor protection laws. Dumping an employee and their family in the desert to die really brings home the meaning of "terminating" said employee.
Which didn't actually happen. (See my response to Scott on the subject.)
Don't forget that if you count the years, Ishmael was old enough to have had his bar mitzvah already. Depending on how long Isaac was breastfed, Ishmael might have been 17. Hagar carrying him is a hilarious little narrative turn.
It's already been argued that this is a work of fiction. So that kind of logical inconsistency is to be expected. It's also a portrayal of "moral behavior" by a righteous man, and accepted as such even by those who consider it fiction.
That said, modern urbanites can't really understand the living conditions of a primitive pastoral group. I can't even figure out how old we're supposed to consider Ishmael to be at the time he was abandoned by his father. Only that it was supposed to be an example of moral behavior.
I mostly chimed in with something I thought was funny -- the idea of Hagar carrying a big strapping lad on her back. I would, however, say that the narrative confusion reveals that even long before the text of Genesis was finalized already they were experiencing pathos at the idea of sending a woman and child into the wilderness. I believe that textual scholars usually suppose that the original narrative was about something like clan politics: ishmael out, isaac in. Later, to spice this up (or maybe due to confusion) the bit with Hagar and the infant-seeming Hagar shows up. Thus, Scott's original point about kindness stands.
The greatest difference is that slavery in the American South is exceptionally well *documented*. We know the stories of the slaves, so we see how horrible it was.
With other historical instances of slavery, we only know what the masters have told us. Of course it is a nicer story! But only a naive person would take it at face value.
Even the maters are pretty clear they were shit ima lot of ancient sources.
Outsiders were often just non-people.
To what extent do you think your job allows you to produce freely, as in Karl Marx's free production? That is, to produce with your passion and to self fulfillment?
Reasonably well. I gain more in framework and motivation than I lose in constraints.
(Reposting my argument from the "contra Caplan" thread, because it feels important to me; it goes beyond the specific debate about mental illnesses.)
Economists seem to be in love with the concept of "revealed preferences". Rationalists seem to be in love with the concept of "anticipated experience". Both groups seem to contain smart people, and these concepts seem to be very important for them. So, what is the relation between these two? If you believe in the concept of revealed preferences, what kind of experience does this make you anticipate?
At this moment, my best guess is that in practice this is another motte-and-bailey thing:
Motte:
When people say that they want X, and yet you observe them consistently doing Y instead, your model needs to explain *also* the latter. A model based only on the former would be *incomplete*, and policy proposals based on it are very likely to fail.
For example, you might think "people (say they) want X, so obviously if we just give them more money (or if we give them greater freedom to choose between X and other things, such as Y), people will have more X". But the actual outcome may be more Y. :(
In other words, "wanting X but doing Y" is a puzzle to be solved, before we start proposing changes.
Bailey:
When people say that they want X, and yet you observe them doing Y instead, there is *no* puzzle to solve. People are liars and hypocrites; if you don't know that, you are dumb. They clearly want Y; they only say they want X for signaling reasons (or because they believe that this is a way to get money from you). Case closed.
Anyone asking "but what about people who *genuinely* want X?" is just a simpleton who doesn't get it.
Leaving aside the inflammatory parts of this, isn't the difference easily modeled by noting that microeconomics treats people ("actors") as atomic, without considering internal structure, but that psychology is all about the internal structure?
I suspect there is bunch of unstated assumptions here concerning nature of individual preferences and individuals.
Case A. Suppose an individual has a revealed preference for Y, but from time to time (for example, when they are not doing Y) they strongly state a stated preference of X (could be something as simple as X = not-Y). Moreover, we can observe that individuals with true, revealed preference of not-Y tend to be much more successful, happier and generally more well-adjusted to their environment on many externally observable metrics most people considered indicative of true, revealed preferences; whereas people who demonstrate revealed preference of Y appear miserable on all other metrics other than pursuing Y. It would make sense to deduce that the individual in question currently has a revealed preference of Y, but would like to become a different, changed individual with a revealed preference for not-Y.
One could fill in variable Y with various addictive or self-destructive behaviors. Case A could be called "individual preference are not constant, fixed states".
Case B is a variant of Case A. Lets add to X and Y also activity Z. Z is the activity by which on can change their preference from Y to X, and it needs to be done for sometime before getting to X. We can observe that taking the path Z is rare, because most people are discounting the hypothetical future pleasure from X so much that they immediately jump from Z to back to Y.
This we could cast as, revealed preference for Y is a local maximum, but X would be a global maximum with much higher value; Z is an unpleasant path from Y to X.
We can easily imagine situations where experienced magnitude of Z is related to an external cause or something individual picked up while doing Y.
The bad news is that you can't figure out peoples preferences by asking them because people are hypocritical liars. The worse news is that you can't any other way. According to the Armstrong-Shah arguments, a mumber of rationality-preference combination can result in the same behaviour. Economists "solve" the problem by assuming rationality. Psychiatrists "solve" it by restricting the range of likely preferences...someone who behaves self-destructively probably doesn't have a genuine preference for self destruction.
It's not that "people are hypocritical liars". Some people are, but that's almost irrelevant, because people generally don't know or understand what their preferences are. They've much clearer about what they don't like, though.
Frequently a preference is only revealed by a stimulus. Do you want a piece of apple pie? A hamburger? My guess is that lots of people weren't even thinking about food before they read those questions.
“Revealed preferences” seems to have gone the way many nuanced and narrow concepts have: starting as a useful concept to explain some contradictions in human behavior (people say they love spending time with their kids but can’t wait for them to gone to bed); now it’s just another gotcha to use in arguments, one of those annoying “but-acshully’s”.
I think revealed preference is still VERY useful if one thinks in terms of bundles of options.
So ... maybe I know someone who says that they want to graduate from college, but doesn't seem to be making much progress towards that.
I'd describe this as:
*) They DO want to graduate from college. If they could push a button (or fill out a form or wave a magic wand) and graduate they would totally do this! But,
*) They DON'T want to do the things required to actually graduate from college: Go to class, study, take the tests, whatever.
"Revealed preference" suggests that they don't want the bundle <do the necessary work/graduate from college>.
Does someone want to "save for retirement"? Sure! But maybe not enough to actually not spend 100% of their take-home pay. If they could spend 100% of their take-home pay and ALSO put 20% away for retirement then they would do so. But they won't live on 80% and save 20%.
This can easily turn into a tautology, but I think viewing the choice as between "sets of choices/actions" is still quite useful.
I view the poop situation in SF like this: The SF voters would *prefer* to not have poop on their sidewalks, but not enough to actually do what is necessary to prevent the poop. Again, if they could just push a button and 'no poop' then they would, but that isn't a choice and between the various forms of 'be mean to people and not have poop on the sidewalks' and 'be nice to people and regret the poop' they prefer the second choice.
Where this is useful is to realize the the poop isn't actually the preference. The poop just comes along for the ride with the bundle.
SF poop is a great example of a complex problem where “revealed preferences” framework adds nothing to the understanding of the issue nor provides any decision-making guidance.
"Revealed preference" is a potentially useful idea, that can't be generally used, because you need to understand a huge context around the action for it to be valid. The simplified form of "Well, this poll shows..." is just ... garbage is too strong a term, but it's a statement about what the poll takers were thinking/feeling when they took the poll, and doesn't have that much to do with how they would act in a real situation, where there's a much wider context.
Revealed preferences isn’t really that controversial to me, nor is it just an dry economic argument.
Its simply to judge people by their actions rather than their words. An adage as old as time.
Btw - Your bailey contains its own motte and Bailey - the first sentence is describing revealed preferences relatively well (although the sentence “if you didn’t know that you are dumb” is designed to poison the well on that argument”).
But this is the Bailey
“Anyone asking "but what about people who *genuinely* want X?" is just a simpleton who doesn't get it”
What? Revealed preferences says nothing about people who genuinely want X, and act on it.
To me it seems the greatest danger is when you model other people's choices incorrectly. For example, you assume that they have options X and Y, but actually, they only have the option Y.
So when you observe them doing Y, you conclude: "they clearly prefer Y to X". If they try to explain that your model is wrong, it is too easy to dismiss them as hypocrites.
An exaggerated example: "Poor people are starving because they have a revealed preference not to eat cake. How do I know? I never saw them eating cake, that's how I know. Smart people like me eat cake every day. That's why we don't starve."
In other words, using the concept of revealed preferences too quickly may prevent you from noticing that you are confused. (On the other hand, the concept of "walking a mile in someone's shoes" is a reminder that our models of other people's situations are often incorrect.) How can you notice that your model of other people is wrong, if you automatically dismiss all feedback as lying and hypocrisy?
Yes, this. But even worse, one assumes options X and Y, but in reality the options are Y, A, B, C, and D, an yet somehow the conclusion is "they clearly prefer Y to X".
>Revealed preferences says nothing about people who genuinely want X, and act on it
The concept itself doesn't, but I *think* the parent comment is gesturing at the readiness with which some people judge contradictory behavior as evidence of an occult preference or deception, when often it makes just as much sense to see it as a flawed alignment mechanism between their behavior and their stated (genuine) preferences.
Well not occult, surely, but possibly deception - up to and including self deception.
What about the external design of a Tesla makes me think it's a luxury car, just by looking at it (I'm not at all knowledgeable about cars, but am a normal person so I've seen many cars)? Relatedly, what is it about sports cars that makes me think they're expensive and luxurious, even beautiful? Is it pure signaling? Are those design features expensive to manufacture, making the signal costly and preventing all car makers from making cars that look like that, but are cheap? Or is the signal costly in some other way (inconvenient to the driver, etc.)?
My limited understanding is that despite advances in manufacturing technology, it's easier to make car panels out of simpler rather than more complex shapes. If a single panel is a weird combination of concave and convex with odd creases and things then it's more expensive to manufacture than a simple curved shape. It's still not a huge fraction of the cost of a car, but it's something that you avoid if you're building a car down to a budget, which is why you'll only see simple curves on a cheap car like a Dacia Sandero https://www.topgear.com/car-reviews/dacia/sandero or a Toyota Etios https://en.wikipedia.org/wiki/Toyota_Etios
A Tesla (except the Cybertruck!) has complicated panel shapes, which your brain associates with expensive vehicles.
I believe that any somewhat unique and distinct design that’s combined with a major innovation in design/technology/engineering etc, will automatically turn said design into something iconic that will be perceived as luxury. While the design likely has some objectively beautiful elements to it, I don’t think it would have been able to stand out as much if it were not for all the other factors that make Tesla stand out. In the end the design is just a physical representation of all of that.
Your question just motivated me to finally publish my first Substack article (which had been saved as a draft for a few weeks) - it’s about what makes a product/design iconic and hopefully answers your question in more depth: https://open.substack.com/pub/danieldramani/p/the-anatomy-of-cultural-artifacts?r=9foey&utm_medium=ios&utm_campaign=post
I agree with DD. The fundamentals of EV's vs ICE-powered cars mean they could make geometry changes to the outside that normal cars could not. The front profile is changed by not needing a radiator, for example.
I think the other subtle cue is a deliberate lack of logos and "bling". I.E. many Teslas I see have the "T" logo not in chrome but the same color as the car. These are good design decisions along the Apple aesthetic of "so monochrome we don't even HAVE controls", which I hate in practice, but is au courant to convey wealth and status.
Tesla made it possible for rich liberals to virtue-signal about the environment while also signaling they are rich (a Prius is great but it's kinda for Poors.) Lots of smart people optimized that message, design-wise.
I think it continues to work as signalling for a while when an expensive-to-manufacture feature gets a lot cheaper.
I think it'd be instructive to compare models of VW/Skoda/Audi, since they're all made from the same common platforms
I think design tradeoffs are part of it - if you're selling yourself on cargo space and legroom, then the low, sleek look of a sports car will be counterproductive. If you don't need a huge engine space and a lot of streamlining, then there's no point in having a long wheelbase that makes it harder to park.
But I do think some of it is just how much design effort you're willing to put in. Like, I've driven a 2015 Honda Fit and a 2007 Honda Fit, and the newer one looks much sleeker despite them basically being the same body shape. I don't think there's any reason they couldn't have had the nifty little grooves on the side panels or the newer headlight layout back in 2007, it's just that in 2007 they weren't thinking about how to make a cheap subcompact look "sporty."
Hmm I’m reading the Elon biography by Vance, and he describes the Model S as like a lovechild of an Aston Martin and Maserati. So the design traits the Model S and subsequent Teslas have are associated with other luxury cars.
I think because we know that because cars with those design choices cost a lot, and always have, we associate design choices in them with luxury.
"...the paper as written implies that it’s proven something more exciting than it did." -- sounds like moral decline to me!
*Applauds*
I am trying to catch up with the latest in infinite ethics and relatedly how different types of AGI are likely to react to having internal conceptions of infinity. I've read a few of the highest rated LW posts on the topic like a series of increasingly perverse and destructive games and am starting to get a feel for it. However, I don't know what if any progress has been made sense they were posted.
Additionally, this line of thinking has promoted me to brush up on my general proof writing and some potential specific prerequisites (e.g. I studied the concept of cardinality back in school but couldn't remember what a bijection was till I looked it up). So I am looking for advice on how to catch up. Either good resources for self study or good ways to find tutors (I can afford to pay some money for this but have no clue what the going rates are).
Does anyone have an opinion on how David Sinclair's Lifespan has held up in the years since its publication? In particular, have there been new insights on the supplements that Sinclair not-recommends (NMN, resveratrol, metformin)?
I found https://www.science.org/content/blog-post/speaking-illusions-sirtuins-and-longevity enlightening; I think sirtuins were one of Sinclair's big things and it seems like they might just not work.
Resveratrol is definitely not going to do anything (Sinclair was definitely wrong about that). Metformin and NMN might be good but the evidence isn't very strong.
FWIW, one of the actions of Metformin is to block? kill? senescent cells.
If the action of Metformin isn't very strong, that might mean that senescent cells aren't a good target.