AprilSR

• AprilSR 25 Apr 2024 7:47 UTC

  17 points

  15

  on: Is be­ing a trans woman +20 IQ?

  All the smart trans girls I know were also smart prior to HRT.

• AprilSR 18 Jan 2024 23:22 UTC

  12 points

  on: Pro­jec­tLawful.com: Eliezer’s lat­est story, past 1M words

  I feel like Project Lawful, as well as many of Lintamande’s other glowfic since then, have given me a whole lot deeper an understanding of… a collection of virtues including honor, honesty, trustworthiness, etc, which I now mostly think of collectively as “Law”.

  I think this has been pretty valuable for me on an intellectual level—I think, if you show me some sort of deontological rule, I’m going to give a better account of why/​whether it’s a good idea to follow it than I would have before I read any glowfic.

  It’s difficult for me to separate how much of that is due to Project Lawful in particular, because ultimately I’ve just read a large body of work which all had some amount of training data showing a particular sort of thought pattern which I’ve since learned. But I think this particular fragment of the rationalist community has given me some valuable new ideas, and it’d be great to figure out a good way of acknowledging that.

• AprilSR 14 Jan 2024 23:17 UTC

  10 points

  0

  in reply to: Roko’s comment on: Gen­der Exploration

  i think they presented a pretty good argument that it is actually rather minor

• AprilSR 21 Dec 2023 19:10 UTC

  12 points

  4

  on: Star­ing into the abyss as a core life skill

  While the concept that looking at the truth even when it hurts is important isn’t revolutionary in the community, I think this post gave me a much more concrete model of the benefits. Sure, I knew about the abstract arguments that facing the truth is valuable, but I don’t know if I’d have identified it as an essential skill for starting a company, or as being a critical component of staying in a bad relationship. (I think my model of bad relationships was that people knew leaving was a good idea, but were unable to act on that information—but in retrospect inability to even consider it totally might be what’s going on some of the time.)

• AprilSR 17 Dec 2023 8:09 UTC

  11 points

  9

  on: Align­ment work in anoma­lous worlds

  So if a UFO lands in your backyard and aliens ask if you if you want to go on a magical (but not particularly instrumental) space adventure with them, I think it’s reasonable to very politely decline, and get back to work solving alignment.

  I think I’d probably go for that, actually, if there isn’t some specific reason to very strongly doubt it could possibly help? It seems somewhat more likely that I’ll end up decisive via space adventure than by mundane means, even if there’s no obvious way the space adventure will contribute.

  This is different if you’re already in a position where you’re making substantial progress though.

• AprilSR 13 Dec 2023 0:50 UTC

  3 points

  0

  on: AI Views Snapshots

  Here’s mine

• AprilSR 8 Dec 2023 9:51 UTC

  2 points

  0

  in reply to: faul_sname’s comment on: You’re op­ti­mized for IGF (Source: trust me bro)

  nonetheless, i think the analogy is still suggestive that an AI selectively shaped for whatever might end up deliberately maximizing something else

• AprilSR 8 Dec 2023 4:27 UTC

  4 points

  6

  on: LessWrong Has Agree/​Disagree Vot­ing On All New Com­ment Threads

  i think, in retrospect, this feature was a really great addition to the website.

• AprilSR 9 Oct 2023 8:12 UTC

  3 points

  1

  on: AI Align­ment Break­throughs this week (10/​08/​23)

  This post introduced me to a bunch of neat things, thanks!

• AprilSR 8 Oct 2023 22:50 UTC

  9 points

  7

  in reply to: Roko’s comment on: Sam Alt­man’s sister, An­nie Alt­man, says Sam has (severely) abused her

  There are several comments “suggesting that maybe the cause is mental illness”.

• AprilSR 5 Oct 2023 19:39 UTC

  15 points

  10

  on: Eval­u­at­ing the his­tor­i­cal value mis­speci­fi­ca­tion argument

  But personally, I think having such a standard is both unreasonable and inconsistent with the implicit standard set by essays from Yudkowsky and other MIRI people.

  I think this is largely coming from an attempt to use approachable examples? I could believe that there were times when MIRI thought that even getting something as good as ChatGPT might be hard, in which case they should update, but I don’t think they ever believed that something as good as ChatGPT is clearly sufficient. I certainly never believed that, at least.

• AprilSR 28 Sep 2023 18:16 UTC

  7 points

  3

  on: Petrov Day Ret­ro­spec­tive, 2023 (re: the most im­por­tant virtue of Petrov Day & unilat­er­ally pro­mot­ing it)

  Yes, we told everyone they were in the minority. It’s a “game”.

  I think this is bad. I mean, it’s not that big a deal, but I generally speaking expect messages I receive from The LessWrong Team to not tell falsehoods.

• AprilSR 28 Sep 2023 18:14 UTC

  5 points

  2

  on: Petrov Day Ret­ro­spec­tive, 2023 (re: the most im­por­tant virtue of Petrov Day & unilat­er­ally pro­mot­ing it)

  Hmm.

  I don’t think Avoiding actions that noticeably increase the chance civilization is destroyed is necessarily the most practically-relevant virtue, for most people, but it does seem to me like it’s the point of Petrov day in particular. If we’re recognizing Petrov as a person, I’d say that was Petrov’s key virtue.

  Or maybe I’d say something like “not doing very harmful acts despite incentives to do so”—I think “resisting social pressure” isn’t quite on the mark, but I think it is important to Petrov day that there were strong incentives against what Petrov did.

  I think other virtues are worth celebrating, but I think I’d want to recognize them on different holidays.

• AprilSR 14 Sep 2023 4:52 UTC

  1 point

  0

  in reply to: Wei Dai’s comment on: UDT shows that de­ci­sion the­ory is more puz­zling than ever

  I mean, that’s a thing you might hope to be true. I’m not sure if it actually is true.

• AprilSR 14 Sep 2023 3:50 UTC

  2 points

  1

  in reply to: Wei Dai’s comment on: UDT shows that de­ci­sion the­ory is more puz­zling than ever

  I think, if you had several UDT agents with the same source code, and then one UDT agent with slightly different source code, you might see the unique agent defect.

  I think the CDT agent has an advantage here because it is capable of making distinct decisions from the rest of the population—not because it is CDT.

• AprilSR 14 Sep 2023 3:46 UTC

  1 point

  0

  in reply to: simon’s comment on: UDT shows that de­ci­sion the­ory is more puz­zling than ever

  I’m not sure “original instantiation” is always well-defined

• AprilSR 14 Sep 2023 3:45 UTC

  1 point

  −1

  on: UDT shows that de­ci­sion the­ory is more puz­zling than ever

  I think personally I’d say it’s a clear advancement—it opens up a lot of puzzles, but the naïve intuition corresponding to it it still seems more satisfying than CDT or EDT, even if a full formalization is difficult.

  (Not to comment on whether there might be a better communications strategy for getting the academic community interested.)

• AprilSR 13 Sep 2023 7:22 UTC

  3 points

  0

  on: Should an un­der­grad avoid a ca­pa­bil­ities pro­ject?

  Provided that you make sure you don’t publish some massive capabilities progress—which I think is pretty unlikely for most undergrads—I think the benefits from having an additional alignment-conscious person with relevant skills probably outweighs the very marginal costs of tiny incremental capabilities ideas.

• AprilSR 8 Sep 2023 2:53 UTC

  15 points

  12

  in reply to: aphyer’s comment on: Shar­ing In­for­ma­tion About Nonlinear

  I think a lot of travel expenses?

• AprilSR 8 Sep 2023 0:58 UTC

  3 points

  0

  in reply to: David Mears’s comment on: Shar­ing In­for­ma­tion About Nonlinear

  I was confused by the disagree votes on this comment, so I looked—the comment in question is highest on the default “new and upvoted” sorting, but it isn’t highest on the “top” sorting.