LessWrong 2.0 Reader
View: New · Old · Topnext page (older posts) →
Eliezer Yudkowsky (Eliezer_Yudkowsky) · 2007-02-18T21:23:00.000Z · comments (240)
Eliezer Yudkowsky (Eliezer_Yudkowsky) · 2007-02-25T00:39:33.000Z · comments (78)
Throughout your comment you've been saying a phrase "thirders odds", apparently meaning odds 1:2, not specifying whether per awakening or per experiment. This is underspecified and confusing category which we should taboo.
Yeah, that was sloppy language, though I do like to think more in terms of bets than you do. One of my ways of thinking about these sorts of issues is in terms of "fair bets" - each person thinks a bet with payoffs that align with their assumptions about utility is "fair", and a bet with payoffs that align with different assumptions about utility is "unfair".
I do not claim that. I say that in order to justify not betting differently, thirders have to retroactively change the utility of a bet already made:
I critique thirdism not for making different bets - as the first part of the post explains, the bets are the same, but for their utilities not actually behaving like utilities - constantly shifting back and forth during the experiment, including shifts backwards in time, in order to compensate for the fact that their probabilities are not behaving as probabilities - because they are not sound probabilities as explained in the previous post.
Wait, are you claiming that thirder Sleeping Beauty is supposed to always decline the initial per experiment bet - before the coin was tossed at 1:1 odds? This is wrong - both halfers and thirders are neutral towards such bets, though they appeal to different reasoning why.
OK, I was also being sloppy in the parts you are responding to.
Scenario 1: bet about a coin toss, nothing depending on the outcome (so payoff equal per coin toss outcome)
Scenario 2: bet about a Sleeping Beauty coin toss, payoff equal per awakening
Scenario 3: bet about a Sleeping Beauty coin toss, payoff equal per coin toss outcome
It doesn't matter if it's agreed to before or after the experiment, as long as the payoffs work out that way. Betting within the experiment is one way for the payoffs to more naturally line up on a per-awakening basis, but it's only relevant (to bet choices) to the extent that it affects the payoffs.
Now, the conventional Thirder position (as I understand it) consistently applies equal utilities per awakening when considered from a position within the experiment.
I don't actually know what the Thirder position is supposed to be from a standpoint from before the experiment, but I see no contradiction in assigning equal utilities per awakening from the before-experiment perspective as well.
As I see it, Thirders will only regret a bet (in the sense of considering it a bad choice to enter into ex ante given their current utilities) if you do some kind of bait and switch where you don't make it clear what the payoffs were going to be up front.
But what I'm pointing at, is that thirdism naturally fails to develop an optimal strategy for per experiment bet in technicolor problem, falsly assuming that it's isomorphic to regular sleeping beauty.
Speculation; have you actually asked Thirders and Halfers to solve the problem? (while making clear the reward structure? - note that if you don't make clear what the reward structure is, Thirders are more likely to misunderstand the question asked if, as in this case, the reward structure is "fair" from the Halfer perspective and "unfair" from the Thirder perspective).
Technicolor and Rare Event problems highlight the issue that I explain in Utility Instability under Thirdism - in order to make optimal bets thirders need to constantly keep track of not only probability changes but also utility changes, because their model keeps shifting both of them back and forth and this can be very confusing. Halfers, on the other hand, just need to keep track of probability changes, because their utility are stable. Basically thirdism is strictly more complicated without any benefits and we can discard it on the grounds of Occam's razor, if we haven't already discarded it because of its theoretical unsoundness, explained in the previous post.
A Halfer has to discount their utility based on how many of them there are, a Thirder doesn't. It seems to me, on the contrary to your perspective, that Thirder utility is more stable.
Halfer model correctly highlights the rule how to determine which cases these are and how to develop the correct strategy for betting. Thirder model just keeps answering 1/3 as a broken clock.
... and I in my hasty reading and response I misread the conditions of the experiment (it's a "Halfer" reward structure again). (As I've mentioned before in a comment on another of your posts, I think Sleeping Beauty is unusually ambiguous so both Halfer and Thirder perspectives are viable. But, I lean toward the general perspectives of Thirders on other problems (e.g. SIA seems much more sensible to me than SSA), so Thirderism seems more intuitive to me).
Thirders can adapt to different reward structures but need to actually notice what the reward structure is!
What do you still feel that is unresolved?
the things mentioned in this comment chain. Which actually doesn't feel like all that much, it feels like there's maybe one or two differences in philosophical assumptions that are creating this disagreement (though maybe we aren't getting at the key assumptions).
elizabeth-1 on My Interview With Cade Metz on His Reporting About Slate Star CodexaZMD: Looking at "Silicon Valley's Safe Space", I don't think it was a good article. Specifically, you wrote,
In one post, [Alexander] aligned himself with Charles Murray, who proposed a link between race and I.Q. in "The Bell Curve." In another, he pointed out that Mr. Murray believes Black people "are genetically less intelligent than white people."
End quote. So, the problem with this is that the specific post in which Alexander aligned himself with Murray was not talking about race. It was specifically talking about whether specific programs to alleviate poverty will actually work or not.
I think Zack's description might be too charitable to Scott. From his description I thought the reference would be strictly about poverty. But the full quote includes a lot about genetics and ability to earn money. The full quote is
The only public figure I can think of in the southeast quadrant with me is Charles Murray. Neither he nor I would dare reduce all class differences to heredity, and he in particular has some very sophisticated theories about class and culture. But he shares my skepticism that the 55 year old Kentucky trucker can be taught to code, and I don’t think he’s too sanguine about the trucker’s kids either. His solution is a basic income guarantee, and I guess that’s mine too. Not because I have great answers to all of the QZ article’s problems. But just because I don’t have any better ideas1,2.
Scott doesn't mention race, but it's an obvious implication, especially when quoting someone the NYT crowd views as anathema. I think Metz could have quoted that paragraph, and maybe given the NYT consensus view on him for anyone who didn't know, and readers would think very poorly of Scott[1].
I bring this up for a couple of reasons:
To be clear: that paragraph doesn't make me think poorly of Scott. I personally agree with Scott that genetics influences jobs and income. I like UBI for lots of reasons, including this one. If I read that paragraph I wouldn't find any of the views objectionable (although a little eyebrow raise that he couldn't find an example with a less toxic reputation- but I can't immediately think of another example that fits either).
The only way ChatGPT can control anything is by writing text, so figuring out that it should write the text that should appear in the image seems pretty straightforward. It only needs to rationalize why this would work.
abramdemski on Modern Transformers are AGI, and Human-LevelNo, I was talking about the results. lsusr seems to use the term in a different sense than Scott Alexander or Yann LeCun. In their sense it's not an alternative to backpropagation, but a way of constantly predicting future experience and to constantly update a world model depending on how far off those predictions are. Somewhat analogous to conditionalization in Bayesian probability theory.
I haven't watched the LeCun interview you reference (it is several hours long, so relevant time-stamps to look at would be appreciated), but this still does not make sense to me -- backprop already seems like a way to constantly predict future experience and update, particularly as it is employed in LLMs. Generating predictions first and then updating based on error is how backprop works. Some form of closeness measure is required, just like you emphasize.
jiro on My Interview With Cade Metz on His Reporting About Slate Star CodexThe reason that I can make a statement about journalists based on this is that the New York Times really is big and influential in the journalism profession. On the other hand, Poor Minorities aren't representative of poor minorities.
Not only that, the poor minorities example is wrong in the first place. Even the restricted subset of poor minorities don't all want to steal your company's money. The motte-and-bailey statement isn't even true about the motte. You never even get to the point of saying something that's true about the motte but false about the bailey.
steve2152 on [Linkpost] Practically-A-Book Review: Rootclaim $100,000 Lab Leak DebateWay back in 2020 there was an article A Proposed Origin For SARS-COV-2 and the COVID-19 Pandemic, which I read after George Church tweeted it (!) (without comment or explanation). Their proposal (they call it "Mojiang Miner Passage" theory) in brief was that it WAS a lab leak but NOT gain-of-function. Rather, in April 2012, six workers in a "Mojiang mine fell ill from a mystery illness while removing bat faeces. Three of the six subsequently died." Their symptoms were a perfect match to COVID, and two were very sick for more than four months.
The proposal is that the virus spent those four months adapting to life in human lungs, including (presumably) evolving the furin cleavage site. And then (this is also well-documented) samples from these miners were sent to WIV. The proposed theory is that those samples sat in a freezer at WIV for a few years while WIV was constructing some new lab facilities, and then in 2019 researchers pulled out those samples for study and infected themselves.
I like that theory! I’ve like it ever since 2020! It seems to explain many of the contradictions brought up by both sides of this debate—it’s compatible with Saar’s claim that the furin cleavage site is very different from what’s in nature and seems specifically adapted to humans, but it’s also compatible with Peter’s claim that the furin cleavage site looks weird and evolved. It’s compatible with Saar’s claim that WIV is suspiciously close to the source of the outbreak, but it’s also compatible with Peter’s claim that WIV might not have been set up to do serious GoF experiments. It’s compatible with the data comparing COVID to other previously-known viruses (supposedly). Etc.
Old as this theory is, the authors are still pushing it and they claim that it’s consistent with all the evidence that’s come out since then (see author’s blog). But I’m sure not remotely an expert, and would be interested if anyone has opinions about this. I’m still confused why it’s never been much discussed.
hiddenprior on Open Thread Spring 2024Unsure if there is normally a thread for putting only semi-interesting news articles, but here is a recently posted news article by Wired that seems.... rather inflammatory toward Effective Altruism. I have not read the article myself yet, but a quick skim confirms the title is not only to get clickbait anger clicks, the rest of the article also seems extremely critical of EA, transhumanism, and Rationality.
I am going to post it here, though I am not entirely sure if getting this article more clicks is a good thing, so if you have no interest in reading it maybe don't click it so we don't further encourage inflammatory clickbait tactics.
https://www.wired.com/story/deaths-of-effective-altruism/?utm_source=pocket-newtab-en-us
tailcalled on My Interview With Cade Metz on His Reporting About Slate Star CodexI get that this is an argument one could make. But the reason I started this tangent was because you said:
Here CM doesn’t directly argue that there was any benefit to doxxing; instead he kinda conveys a vibe / ideology that if something is true then it is self-evidently intrinsically good to publish it
That is, my original argument was not in response to the "Anyway, if the true benefit is zero (as I believe), then we don’t have to quibble over whether the cost was big or small" part of your post, it was to the vibe/ideology part.
Where I was trying to say, it doesn't seem to me that Cade Metz was the one who introduced this vibe/ideology, rather it seems to have been introduced by rationalists prior to this, specifically to defend tinkering with taboo topics.
Like, you mention that Cade Metz conveys this vibe/ideology that you disagree with, and you didn't try to rebut I directly, I assumed because Cade Metz didn't defend it but just treated it as obvious.
And that's where I'm saying, since many rationalists including Scott Alexander have endorsed this ideology, there's a sense in which it seems wrong, almost rude, to not address it directly. Like a sort of Motte-Bailey tactic.
jiro on My Interview With Cade Metz on His Reporting About Slate Star Codexit seems really unlikely that he’s gotten any better at even the grammar of rationalist communication.
You don't need to use rationalist grammar to convince rationalists that you like them. You just need to know what biases of theirs to play upon, what assumptions they're making, how to reassure them, etc.
The skills for pretending to be someone's friend are very different from the skills for acting like them.
mishka on Towards White Box Deep LearningThanks, this is very interesting.
I wonder if this approach is extendable to learning to predict the next word from a corpus of texts...
The first layer might perhaps still be embedding from words to vectors, but what should one do then? What would be a possible minimum viable dataset?
Perhaps, in the spirit of PoC of the paper, one might consider binary sequences of 0s and 1s, and have only two words, 0 and 1, and ask what would it take to have a good predictor of the next 0 or 1 given a long sequence of those as a context. This might be a good starting point, and then one might consider different examples of that problem (different examples of (sets of) sequences of 0 and 1 to learn from).