Instruction-following AGI is easier and more likely than value aligned AGI

Seth Herd15 May 2024 19:38 UTC

30 points

6 comments12 min readLW link

Linear infra-Bayesian Bandits

Vanessa Kosoy10 May 2024 6:41 UTC

38 points

5 comments1 min readLW link

(arxiv.org)

AI Safety Strategies Landscape

Charbel-Raphaël9 May 2024 17:33 UTC

29 points

1 comment42 min readLW link

Visualizing neural network planning

Nevan Wichers, Victor Tao, Fazl and Riccardo Volpato

9 May 2024 6:40 UTC

4 points

0 comments5 min readLW link

AXRP Episode 31 - Singular Learning Theory with Daniel Murfet

DanielFilan7 May 2024 3:50 UTC

68 points

4 comments71 min readLW link

Uncovering Deceptive Tendencies in Language Models: A Simulated Company AI Assistant

Olli Järviniemi and evhub

6 May 2024 7:07 UTC

82 points

4 comments1 min readLW link

(arxiv.org)

Mechanistic Interpretability Workshop Happening at ICML 2024!

Neel Nanda, LawrenceC and Fazl

3 May 2024 1:18 UTC

48 points

6 comments1 min readLW link

Take SCIFs, it’s dangerous to go alone

latterframe, Jeffrey Ladish and schroederdewitt

1 May 2024 8:02 UTC

34 points

1 comment3 min readLW link

AXRP Episode 30 - AI Security with Jeffrey Ladish

DanielFilan1 May 2024 2:50 UTC

25 points

0 comments79 min readLW link

Mechanistically Eliciting Latent Behaviors in Language Models

Andrew Mack and TurnTrout

30 Apr 2024 18:51 UTC

164 points

37 comments45 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

59 points

13 comments17 min readLW link

Towards a formalization of the agent structure problem

Alex_Altair29 Apr 2024 20:28 UTC

52 points

4 comments14 min readLW link

AISC9 has ended and there will be an AISC10

Linda Linsefors29 Apr 2024 10:53 UTC

62 points

4 comments2 min readLW link

[Aspiration-based designs] Outlook: dealing with complexity

Jobst Heitzig, jossoliver, thomasfinn and Simon Dima

28 Apr 2024 13:06 UTC

13 points

3 comments2 min readLW link

[Aspiration-based designs] 3. Performance and safety criteria, and aspiration intervals

Jobst Heitzig28 Apr 2024 13:04 UTC

10 points

0 comments12 min readLW link

[Aspiration-based designs] 2. Formal framework, basic algorithm

Jobst Heitzig, Simon Dima and Simon Fischer

28 Apr 2024 13:02 UTC

16 points

2 comments16 min readLW link

[Aspiration-based designs] 1. Informal introduction

B Jacobs, Jobst Heitzig, Simon Fischer and Simon Dima

28 Apr 2024 13:00 UTC

40 points

4 comments8 min readLW link

Constructability: Plainly-coded AGIs may be feasible in the near future

Épiphanie Gédéon and Charbel-Raphaël

27 Apr 2024 16:04 UTC

66 points

12 comments13 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

191 points

79 comments10 min readLW link

Superposition is not “just” neuron polysemanticity

LawrenceC26 Apr 2024 23:22 UTC

53 points

4 comments13 min readLW link