philip_b

Reneg­ing proso­cially by Dun­can Sabien

• philip_b 13 Nov 2022 22:37 UTC

  47 points

  14

  on: The Align­ment Com­mu­nity Is Cul­turally Broken

  I am (was) an X% researcher, where X<Y. I wish I had given up on AI safety earlier. I suspect it would’ve been better for me if AI safety resources explicitly said things like “if you’re less than Y, don’t even try”, although I’m not sure if I would’ve believed them. Now, I’m glad that I’m not trying to do AI safety anymore and instead I just work at a well paying relaxed job doing practical machine learning. So, I think pushing too many EAs into AI safety will lead to those EAs suffering much more, which happened to me, so I don’t want that to happen and I don’t want the AI Alignment community to stop saying “You should stay if and only if you’re better than Y”.

  Actually, I wish there were more selfish-oriented resources for AI Alignment. Like, with normal universities and jobs, people analyze how to get into them, have a fulfilling career, earn good money, not burn out, etc. As a result, people can read this and properly analyze if it makes sense for them to try to get into jobs or universities for their own food. But with a career in AI safety, this is not the case. All the resources look out not only for the reader, but also for the whole EA project. I think this can easily burn people.

Clas­sifi­ca­tion of AI al­ign­ment re­search: de­con­fu­sion, “good enough” non-su­per­in­tel­li­gent AI al­ign­ment, su­per­in­tel­li­gent AI alignment

• philip_b 17 Oct 2021 10:12 UTC

  35 points

  0

  in reply to: AnnaSalamon’s comment on: My ex­pe­rience at and around MIRI and CFAR (in­spired by Zoe Curzi’s writeup of ex­pe­riences at Lev­er­age)

  To my understanding, since the time when the events described in the OP took place, MIRI and CFAR have been very close and getting closer and closer. As far as I see it, nowadays CFAR is about 60% a hiring ground for MIRI and only 40% something else, though I could be wrong. Since you’re one of the leaders of CFAR, that makes you one of the leading people behind all those things the OP is critical of.

  The OP even writes that she thought and thinks CFAR was corrupt in 2017:

  Both these cases are associated with a subgroup splitting off of the CFAR-centric rationality community due to its perceived corruption, centered around Ziz. (I also thought CFAR was pretty corrupt at the time, and I also attempted to split off another group when attempts at communication with CFAR failed; I don’t think this judgment was in error, though many of the following actions were; …)

  Here she mentions Ziz also thinking that CFAR was corrupt, and I remember that in her blog, Ziz thought you being in the center of said corruption.

  So, how all is this compatible with you agreeing with the OP?

• philip_b 24 Jun 2024 13:02 UTC

  32 points

  11

  on: On Claude 3.5 Sonnet

  They commit to not using your data to train their models without explicit permission.

  I’ve just registered on their website because of this article. During registration, I was told that conversations marked by their automated system that overlooks if you are following their terms of use are regularly overlooked by humans and used to train their models.

AI Safety Pr­ereq­ui­sites Course: Re­vamp and New Lessons

• philip_b 17 Oct 2021 17:59 UTC

  24 points

  0

  in reply to: ChristianKl’s comment on: My ex­pe­rience at and around MIRI and CFAR (in­spired by Zoe Curzi’s writeup of ex­pe­riences at Lev­er­age)

  That would make them more vulnerable to claims that they use organizational mind control on their employees, and at the same time make it more likely that they would actually use it.

• philip_b 18 Sep 2020 9:59 UTC

  23 points

  0

  on: Covid 9/​17: It’s Worse

  I’ve asked Zvi what he thinks about long term consequences of being ill. Due to his answer, my current thinking, which I use to calculate the cost of COVID-19 to myself in dollars, is as follows. COVID-19 long term consequences for myself have 2 components: something that lasts about half a year, and something that’s permanent. Or at least modelling it as if it has 2 components is not too bad.

  The 1st component contains strong fatigue, low grade fever, headaches, or loss of taste and smell and has probability 3% given covid. The 2nd component is permanent lung, heart, or brain damage and I guess has probability about 0.5% given covid. However, this probability estimate is very uncertain and can easily change when new data arrives.

  I’ve eyeballed DALY loss estimates for various diseases according to www.jefftk.com/​gbdweights2010.pdf (which is a DALY estimate study cited by Doing Good Better) and thought. Due to this I’ve got estimates of how bad those two components if they happen are:

  If the 1st component happens, for its duration I will lose 20% of my well-being (as measured in DALY/​QALY) and 30% of my productivity. If the 2nd component happens, then for the rest of my life I will lose 8% of my well-being and 10% of my productivity.

  If you want more details about how I got these percentages, then I can only say what rows in table 2 of that study I found relevant. They are

  • Illness—Coefficient (lower is better, no adverse effects is 0%, death is 100%) - My comment

  • Infectious disease: post-acute consequences (fatigue, emotional lability, insomnia) − 26% - The 1st component is basically this

  • COPD and other chronic respiratory diseases: mild − 1.5% - The 2nd component may realize as this

  • COPD and other chronic respiratory diseases: moderate − 19% - The 2nd component may realize as this

  • Heart failure: Mild − 4% - The 2nd component may realize as this

• philip_b 9 Sep 2025 19:52 UTC

  21 points

  −7

  on: Obli­gated to Respond

  I don’t think that if you don’t respond to a comment arguing with you, people will think you’ve lost the argument. I wouldn’t think like that. I would just evaluate your argument on my own and I would evaluate the counterargument in the comment on my own. I don’t bother to respond to comments very often and I haven’t seen anything bad come out of it.

[Question] How to de­ter­mine if my sym­pa­thetic or my parasym­pa­thetic ner­vous sys­tem is cur­rently dom­i­nant?

• philip_b 19 Dec 2021 20:14 UTC

  20 points

  0

  in reply to: Vlad Sitalo’s comment on: Con­sider Tak­ing Zinc Every Time You Travel

  During these 3 months, I’ve gone through one or two packs of 30 lozenges each, not sure. Yeah, I was sick a lot and worried, wondering if I am getting sick or not, even more. I suspect that Life Extension peppermint lozenges hurt my teeth worse than anything else I regularly consume. Perhaps they’re made of sugar? I haven’t checked. As for helping with common cold, I have no idea if they are helping. Maybe, slightly. In the beginning I thought that maybe I am noticing some positive effect, but it could easily be placebo. I also have a hunch that maybe they help with throat symptoms but not with nose symptoms.

  What links here?

  • philh's comment on Is this info on zinc lozenges ac­cu­rate? by philh (30 Dec 2021 19:26 UTC; 2 points)

• philip_b 6 Jul 2022 17:24 UTC

  18 points

  10

  on: Car­ry­ing the Torch: A Re­sponse to Anna Sala­mon by the Guild of the Rose

  I just want to say that your described solution to “Problem 1: Differentiating effective interventions from unfalsifiable woo” suggests to me that your curriculum would be mostly useless for me, and maybe for many other people as well, because it won’t go deep enough. I think either I’ve already gotten everything I can get from shallow interventions “like better nutrition, using your speaking voice more effectively, improving your personal financial organization, emergency preparedness, and implementing a knowledge management system”, or they were never that good in the first place. Personally, I am focusing on psychotherapy right now. It’s unfortunate that it consists mostly of borderline-unfalsifiable woo but that’s all we’ve got.

• philip_b 21 Jul 2021 11:29 UTC

  18 points

  0

  on: My Mar­riage Vows

  Security mindset, here we go.

  I will never set out to deceive my [spouse] on purpose without [pronoun]’s unambiguous consent, without exception.

  Perhaps you two will realize that it’s better for you if your partner deceives you in some class of situations for stupid-monkey-brain reasons. I guess you can patch the agreement then by consenting to such deception.

  Another potential failure mode: you will think that you’re not deceiving your partner in some area while actually deceiving them. According to “The Elephant in the Brain”, this is probable. From having read the vows, I am unsure how they are supposed to treat such a situation. Also, maybe in such a situation your partner will start despising the vows thinking that it’s unfair that you’re better at deceiving-without-knowing-that-you’re-deceiving than them and that because of these, the vows are better for you. Or it could be vice versa.

  Also, for elephant-in-the-brain reasons, I think it would be good to make the agreement such that there would be some incentives to not act against your partner via unconscious elephant-in-the-brain mechanisms.

  The only exception to the latter is when this information was given to me in confidence by a third party as part of an agreement which was made in compliance with all Vows

  This might make third parties less likely to tell you important things, since you might tell your spouse.

  I will also never withhold information that [pronoun] would in hindsight prefer to know.

  What happens if someone learns about this agreement of yours and thus kidnaps and tortures your spouse until they tell the kidnapper all your passwords or something like that? Suppose your spouse didn’t know your passwords before this event and now they’re on the phone and asking for your passwords. Are you obligated to give them your passwords because right now they prefer to know? Or are you free form the obligation because before this actually happened, both you and your spouse would prefer that you don’t give passwords?

  Another thing, I think this whole agreement models you as a rational agent with a utility function. And it might become bad for you if you start thinking about yourself another way, e.g. if you start seeing yourself less agentic, less rational, with more monkey-brain bugs.

Hard Prob­lems in Cryp­tocur­rency: Five Years Later—Buterin

• philip_b 19 Dec 2020 11:31 UTC

  17 points

  0

  on: LessWrong/​EA New Year’s Ul­tra Party

  If I don’t use Facebook, what do I need to subscribe to get updates? By updates I mean things like “Calendar of activities… we’ll share the spreadsheet shortly”. Can you post all updates in the comments of this post? In that case I’ll subscribe to new comments.

Fun­da­men­tals of For­mal­i­sa­tion Level 3: Set The­o­retic Re­la­tions and Enumerability

• philip_b 3 May 2021 14:18 UTC

  14 points

  1

  on: The Loud­est Alarm Is Prob­a­bly False

  For a data point, after having read the first paragraph I looked for examples and counterexamples. I found 1 example where a person strongly worries they are X while actually they’re anti-X (just like orthonormal describes), 2 examples where a person strongly worries they’re X and they’re indeed X, and 3 examples where they worry they’re X but actually they’re normal, i.e. between X and anti-X.

• philip_b 14 Sep 2019 12:30 UTC

  14 points

  0

  on: crab­man’s Shortform

  A competition on solving math problems via AI is coming. https://​​imo-grand-challenge.github.io/​​

  • The problems are from the International math olympiad (IMO)

  • They want to formalize all the problems in Lean (theorem prover) language. They haven’t figured out how to do that, e.g. how to formalize problems of form “determine the set of objects satisfying the given property”, as can be seen in https://​​github.com/​​IMO-grand-challenge/​​formal-encoding/​​blob/​​master/​​design/​​determine.lean

  • A contestant must submit a computer program that will take a problem’s description as input and output a solution and its proof in Lean.

  I would guess that this is partly a way to promote Lean. I think it would be interesting to pose questions about this on metaculus.

Fun­da­men­tals of For­mal­i­sa­tion Level 5: For­mal Proof

• philip_b 15 May 2023 4:39 UTC

  13 points

  6

  on: The Light­cone The­o­rem: A Bet­ter Foun­da­tion For Nat­u­ral Ab­strac­tion?

  Can you formulate the theorem statement in a precise and self-sufficient way that is usually used in textbooks and papers so that a reader can understand it just by reading it and looking up the used definitions?