Mechanistic Interpretability Workshop Happening at ICML 2024!

Neel Nanda, LawrenceC and Fazl

3 May 2024 1:18 UTC

35 points

1 comment1 min readLW link

[Question] Which skincare products are evidence-based?

Vanessa Kosoy2 May 2024 15:22 UTC

58 points

4 comments1 min readLW link

Q&A on Proposed SB 1047

Zvi2 May 2024 15:10 UTC

53 points

1 comment44 min readLW link

(thezvi.wordpress.com)

Introducing AI Lab Watch

Zach Stein-Perlman30 Apr 2024 17:00 UTC

169 points

7 comments1 min readLW link

(ailabwatch.org)

Mechanistically Eliciting Latent Behaviors in Language Models

Andrew Mack and TurnTrout

30 Apr 2024 18:51 UTC

135 points

24 comments45 min readLW link

ACX Covid Origins Post convinced readers

ErnestScribbler1 May 2024 13:06 UTC

69 points

5 comments2 min readLW link

Why is AGI/ASI Inevitable?

DeathlessAmaranth2 May 2024 18:27 UTC

11 points

3 comments1 min readLW link

Let’s Design A School, Part 2.1 School as Education—Structure

Sable2 May 2024 22:04 UTC

4 points

0 comments10 min readLW link

(affablyevil.substack.com)

[Question] Shane Legg’s necessary properties for every AGI Safety plan

jacquesthibs1 May 2024 17:15 UTC

54 points

10 comments1 min readLW link

Ironing Out the Squiggles

Zack_M_Davis29 Apr 2024 16:13 UTC

138 points

27 comments11 min readLW link

CCS: Counterfactual Civilization Simulation

Pi Rogers2 May 2024 22:54 UTC

2 points

0 comments2 min readLW link

LessWrong Community Weekend 2024, open for applications

UnplannedCauliflower and jt

1 May 2024 10:18 UTC

58 points

0 comments7 min readLW link

Why I’m doing PauseAI

Joseph Miller30 Apr 2024 16:21 UTC

88 points

7 comments4 min readLW link

Please stop publishing ideas/insights/research about AI

Tamsin Leake2 May 2024 14:54 UTC

12 points

41 comments4 min readLW link

An explanation of evil in an organized world

KatjaGrace2 May 2024 5:20 UTC

25 points

7 comments2 min readLW link

(worldspiritsockpuppet.com)

Manifund Q1 Retro: Learnings from impact certs

Austin Chen1 May 2024 16:48 UTC

39 points

1 comment1 min readLW link

Questions for labs

Zach Stein-Perlman30 Apr 2024 22:15 UTC

63 points

9 comments8 min readLW link

[Question] Can stealth aircraft be detected optically?

Yair Halberstadt2 May 2024 7:47 UTC

17 points

21 comments1 min readLW link

Refusal in LLMs is mediated by a single direction

Andy Arditi, Oscar Obeso, Aaquib111, wesg and Neel Nanda

27 Apr 2024 11:13 UTC

170 points

66 comments10 min readLW link

Transcoders enable fine-grained interpretable circuit analysis for language models

Jacob Dunefsky, Philippe Chlenski and Neel Nanda

30 Apr 2024 17:58 UTC

54 points

11 comments17 min readLW link