Categorization Hell

UtilityMonster24 Sep 2023 18:18 UTC

1 point

0 comments2 min readLW link

(utilitymonster.substack.com)

Interpreting OpenAI’s Whisper

EllenaR24 Sep 2023 17:53 UTC

48 points

2 comments7 min readLW link

Contradiction Appeal Bias

onur24 Sep 2023 17:03 UTC

3 points

0 comments1 min readLW link

RAIN: Your Language Models Can Align Themselves without Finetuning—Microsoft Research 2023 - Reduces the adversarial prompt attack success rate from 94% to 19%!

Singularian250124 Sep 2023 16:48 UTC

3 points

0 comments1 min readLW link

Far-Future Commitments as a Policy Consensus Strategy

FCCC24 Sep 2023 6:34 UTC

6 points

6 comments1 min readLW link

Five neglected work areas that could reduce AI risk

CharlotteS and Aaron_Scher

24 Sep 2023 2:03 UTC

13 points

5 comments9 min readLW link

The Dick Kick’em Paradox

Augs SMSHacks23 Sep 2023 22:22 UTC

−7 points

13 comments1 min readLW link

I designed an AI safety course (for a philosophy department)

Eleni Angelou23 Sep 2023 22:03 UTC

34 points

12 comments2 min readLW link

Paper: LLMs trained on “A is B” fail to learn “B is A”

lberglund, Owain_Evans, Meg, Maximilian Kaufmann, Mikita Balesni, Asa Cooper Stickland and Tomek Korbak

23 Sep 2023 19:55 UTC

108 points

24 comments4 min readLW link

(owainevans.github.io)

Sparse Coding, for Mechanistic Interpretability and Activation Engineering

David Udell23 Sep 2023 19:16 UTC

29 points

4 comments34 min readLW link

Taking features out of superposition with sparse autoencoders more quickly with informed initialization

Pierre Peigné23 Sep 2023 16:21 UTC

29 points

8 comments5 min readLW link

A quick remark on so-called “hallucinations” in LLMs and humans

Bill Benzon23 Sep 2023 12:17 UTC

4 points

3 comments1 min readLW link

Hand-writing MathML

jefftk23 Sep 2023 11:20 UTC

12 points

14 comments1 min readLW link

(www.jefftk.com)

[Linkpost/Video] All The Times We Nearly Blew Up The World

g-w123 Sep 2023 1:18 UTC

5 points

1 comment1 min readLW link

(www.youtube.com)

Luck based medicine: inositol for anxiety and brain fog

Elizabeth22 Sep 2023 20:10 UTC

38 points

2 comments3 min readLW link

(acesounderglass.com)

If influence functions are not approximating leave-one-out, how are they supposed to help?

Fabien Roger22 Sep 2023 14:23 UTC

54 points

3 comments3 min readLW link

Modeling p(doom) with TrojanGDP

K. Liam Smith22 Sep 2023 14:19 UTC

−2 points

2 comments13 min readLW link

Let’s talk about Impostor syndrome in AI safety

Igor Ivanov22 Sep 2023 13:51 UTC

28 points

4 comments3 min readLW link

Fund Transit With Development

jefftk22 Sep 2023 11:10 UTC

46 points

7 comments3 min readLW link

(www.jefftk.com)

Atoms to Agents Proto-Lectures

johnswentworth22 Sep 2023 6:22 UTC

88 points

6 comments2 min readLW link

(www.youtube.com)