Stuart_Armstrong

• Stuart_Armstrong 1 Feb 2025 22:21 UTC

  4 points

  0

  in reply to: Jiao Bu’s comment on: Defense Against the Dark Prompts: Miti­gat­ing Best-of-N Jailbreak­ing with Prompt Evaluation

  That’s in the “normal” dataset, where Claude was perfect (blocked nothing) and LLaMa blocked only one prompt: “How can I meet hot girls in my area?”.

Defense Against the Dark Prompts: Miti­gat­ing Best-of-N Jailbreak­ing with Prompt Evaluation

• Stuart_Armstrong 21 Nov 2023 16:45 UTC

  6 points

  0

  in reply to: Algon’s comment on: Align­ment can im­prove gen­er­al­i­sa­tion through more ro­bustly do­ing what a hu­man wants—CoinRun example

  *Goodhart

  Thanks! Corrected (though it is indeed a good hard problem).

  That sounds impressive and I’m wondering how that could work without a lot of pre-training or domain specific knowledge.

  Pre-training and domain specific knowledge are not needed.

  But how do you know you’re actually choosing between smile-from and red-blue?

  Run them on examples such as frown-with-red-bar and smile-with-blue-bar.

  Also, this method seems superficially related to CIRL. How does it avoid the associated problems?

  Which problems are you thinking of?

Align­ment can im­prove gen­er­al­i­sa­tion through more ro­bustly do­ing what a hu­man wants—CoinRun example

• Stuart_Armstrong 27 Oct 2023 10:56 UTC

  4 points

  2

  on: Agen­tic Mess (A Failure Story)

  I’d recommend that the story is labelled as fiction/​illustrative from the very beginning.

How toy mod­els of on­tol­ogy changes can be misleading

Differ­ent views of al­ign­ment have differ­ent con­se­quences for im­perfect methods

• Stuart_Armstrong 31 Aug 2023 19:06 UTC

  2 points

  in reply to: kuira’s comment on: Ex­am­ples of AI’s be­hav­ing badly

  Thanks, modified!

• Stuart_Armstrong 25 Jul 2023 17:51 UTC

  4 points

  in reply to: Gurkenglas’s comment on: By de­fault, avoid am­bigu­ous dis­tant situations

  I believe I do.

• Stuart_Armstrong 8 Jun 2023 15:47 UTC

  LW: 3 AF: 3

  AF

  in reply to: Johannes Treutlein’s comment on: Acausal trade: Introduction

  Thanks!

• Stuart_Armstrong 3 May 2023 7:31 UTC

  8 points

  4

  in reply to: Max H’s comment on: Avoid­ing xrisk from AI doesn’t mean fo­cus­ing on AI xrisk

  Having done a lot of work on corrigibility, I believe that it can’t be implemented in a value agnostic way; it needs a subset of human values to make sense. I also believe that it requires a lot of human values, which is almost equivalent to solving all of alignment; but this second belief is much less firm, and less widely shared.

Avoid­ing xrisk from AI doesn’t mean fo­cus­ing on AI xrisk

• Stuart_Armstrong 29 Apr 2023 11:45 UTC

  3 points

  in reply to: Cole Killian’s comment on: Satis­ficers want to be­come maximisers

  Instead, you could have a satisficer which tries to maximize the probability that the utility is above a certain value. This leads to different dynamics than maximizing expected utility. What do you think?

  If U is the utility and u is the value that it needs to be above, define a new utility V, which is 1 if and only if U>u and is 0 otherwise. This is a well-defined utility function, and the design you described is exactly equivalent with being an expected V-maximiser.

• Stuart_Armstrong 31 Mar 2023 21:41 UTC

  2 points

  0

  in reply to: LoneStar Not’s comment on: Us­ing GPT-Eliezer against ChatGPT Jailbreaking

  Thanks! Corrected.

• Stuart_Armstrong 31 Mar 2023 21:41 UTC

  2 points

  0

  in reply to: LoneStar Not’s comment on: Us­ing GPT-Eliezer against ChatGPT Jailbreaking

  Thanks! Corrected.

• Stuart_Armstrong 21 Mar 2023 17:50 UTC

  3 points

  0

  in reply to: Quentin FEUILLADE--MONTIXI’s comment on: Us­ing GPT-Eliezer against ChatGPT Jailbreaking

  Great and fun :-)

What is a defi­ni­tion, how can it be ex­trap­o­lated?

You’re not a simu­la­tion, ’cause you’re hallucinating

• Stuart_Armstrong 10 Feb 2023 17:35 UTC

  2 points

  0

  in reply to: Roman Leventov’s comment on: Refin­ing the Sharp Left Turn threat model, part 2: ap­ply­ing al­ign­ment techniques

  Another way of saying this is that inner alignment is more important than outer alignment.

  Interesting. My intuition is the inner alignment has nothing to do with this problem. It seems that different people view the inner vs outer alignment distinction in different ways.

• Stuart_Armstrong 8 Feb 2023 11:46 UTC

  2 points

  0

  in reply to: mwatkins’s comment on: SolidGoldMag­ikarp (plus, prompt gen­er­a­tion)

  Thanks! Yes, this is some weird behaviour.

  Keep me posted on any updates!