Alex Darby

Karma: 43

Alex Darby 1 Apr 2026 19:08 UTC
12 points
0
on: Lesswrong Liberated
oooooh columns
is like lesswrong proper, but with three columns instead of one

because more is better

Alex Darby 31 Mar 2026 12:53 UTC
1 point
0
in reply to: DaystarEld’s comment on: Folie à Machine: LLMs and Epistemic Capture
Interesting. I agree most people don’t do that mental move, although it’s instinctive for me.
Not sure about whether “most people who read LessWrong” do it habitually and/or have the ability to do it. Is entirely possible the answer to that is also no, and I’m just typical-mind-fallacy-ing.
Spoiler-heavy link to the cleanest “explanation by example” of this mental action I can think of quickly, for people to reference if they want more details (from Yudkowsky’s writings)

https://www.glowfic.com/posts/6075?page=20

a one-line snippet (spoiler-free):
Wherever your attempt to steer {the world} ends up, {name} will ask if that was the point of the whole plan, no matter what cleverness you essay along the way.

Alex Darby 31 Mar 2026 10:08 UTC
1 point
0
on: Folie à Machine: LLMs and Epistemic Capture
I don’t yet fully understand how LLM ‘psychosis’ get past the “single point of failure check”.

If I’m talking to a human (let’s call him Sam), and these conversations lead me somewhere unusual, my standard check is “suspend all arguments and evidence, and suppose my current mental state/beliefs are in fact what Sam was originally optimising for”.

Applying this to LLM ‘psychosis’, this means if I’m doing LLM-aided thinking and end up somewhere novel or unusual, we check with “suspend all arguments—is there anything in LLM RLHF that makes what I’m currently doing generate reward for the LLM (where it won’t also solve the problem I’m thinking about)”.

Unsure how to think about this.

Alex Darby 26 Mar 2026 0:31 UTC
3 points
0
in reply to: 0xA’s comment on: $1 billion is not enough; OpenAI Foundation must start spending tens of billions each year
Socratic question—what does being (especially within the in-group community) publicly being outraged at Altman achieve?
Can follow up with more thoughts later, but I am interested in your views as to the utility of various group postures (we can, for the sake of doing the interesting part of the discussion and not the boring part, assume we don’t need more evidence and that your claim is true).

Alex Darby 28 Jan 2026 14:49 UTC
2 points
0
in reply to: Boaz Barak’s comment on: Thoughts on Claude’s Constitution
Agreed. I think a more measured phrasing is “I am confident that across a significant number of current AI companies, in the near future, the models are more similar than one would expect from reading the difference between (representative example) Claude’s Constitution and OpenAI’s Model Spec.”

I think I am personally holding the strong conclusion (that you are pushing back on) as plausible-enough and important-if-true-enough that I want to be tracking how true I think it is as I get more information.

If even moderately weak forms of “instrumental convergence of model design” end up clearly false in O(5-years) time, I would be surprised but not confused.

If anyone with more context on modern AI models than me disagrees, please say so; me knowing multiple perspectives on all of this is useful and makes my world-models better.

Alex Darby 28 Jan 2026 10:45 UTC
2 points
0
on: Thoughts on Claude’s Constitution
Epistemic Status: You Get About Five Words; explaining my top takeaway from the post.
Of course this difference is to some degree not as much a difference in the model behavior training of either company as a difference in the documents that each choose to make public.
This sentence weakly implies the Five Words: “instrumental convergence of model design”. If we take this principle further, we get the idea that Claude N, ChatGPT N and Gemini N are all likely to be very similar as N increases.
This has implications for alignment work that I’m not quite sure how to think about:
- Any current technique that only works on some SoTA models is brittle;
- If Lab X solves a key part of the alignment problem internally (e.g. corrigibility), either the change makes the models more robustly useful, and is adopted by other labs quickly, or it makes the model slightly worse, and there is strong pressure to leave the work in a “safety-related bubble”;
- ???

Alex Darby 8 Dec 2025 20:19 UTC
11 points
0
in reply to: Gyrodiot’s comment on: 2025 Unofficial LessWrong Census/Survey
Survey completed!

Alex Darby 11 Oct 2025 23:16 UTC
15 points
4
in reply to: Keenan Pepper’s comment on: Hubris & Control
I believe Duncan’s posts are cross-posted from his Substack to LessWrong due to popular demand. In that sense, Duncan can still be viewed as somewhat active.
However, the “(inactive)” in the name serves a purpose, which (very confident inference) is to public declare Duncan’s relationship with the LessWrong comments section, which (reasonable inference) is somewhere between “I don’t participate in the LessWrong comments section” and “I find some comments valuable and some comments anti-valuable, but want to specifically discharge my usual social obligation to read and respond to comments on my posts because this would be net-negative for me.”
[comment epistemic status: quick and somewhat imprecise to serve the purpose of quickly answering the implied question of Keenen’s comment.]