List your AI X-Risk cruxes!

Aryeh Englander28 Apr 2024 18:26 UTC

14 points

0 comments2 min readLW link

Things I tell myself to be more agentic

DMMF28 Apr 2024 17:44 UTC

4 points

0 comments3 min readLW link

(danfrank.ca)

[Aspiration-based designs] 1. Informal introduction

B Jacobs, Jobst Heitzig, Simon Fischer and Simon Dima

28 Apr 2024 13:00 UTC

22 points

0 comments8 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

126 points

29 comments10 min readLW link

Estimating the Number of Players from Game Result Percentages

Daniel L28 Apr 2024 17:42 UTC

1 point

0 comments1 min readLW link

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

Jobst Heitzig, Simon Dima and Simon Fischer

28 Apr 2024 13:02 UTC

14 points

0 comments16 min readLW link

The Science Algorithm—AISC 2024 Final Presentation

Johannes C. Mayer28 Apr 2024 14:55 UTC

7 points

0 comments1 min readLW link

(www.youtube.com)

[Aspiration-based designs] Outlook: dealing with complexity

Jobst Heitzig, jossoliver and thomasfinn

28 Apr 2024 13:06 UTC

11 points

0 comments2 min readLW link

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

Jobst Heitzig28 Apr 2024 13:04 UTC

9 points

0 comments12 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

59 points

8 comments13 min readLW link

On Not Pulling The Ladder Up Behind You

Screwtape26 Apr 2024 21:58 UTC

101 points

5 comments9 min readLW link

So What’s Up With PUFAs Chemically?

J Bostock27 Apr 2024 13:32 UTC

51 points

21 comments6 min readLW link

Duct Tape security

Isaac King26 Apr 2024 18:57 UTC

66 points

8 comments5 min readLW link

[Question] Examples of Highly Counterfactual Discoveries?

johnswentworth23 Apr 2024 22:19 UTC

160 points

85 comments1 min readLW link

Superposition is not “just” neuron polysemanticity

LawrenceC26 Apr 2024 23:22 UTC

47 points

3 comments13 min readLW link

Thoughts on seed oil

dynomight20 Apr 2024 12:29 UTC

261 points

82 comments17 min readLW link

(dynomight.net)

The first future and the best future

KatjaGrace25 Apr 2024 6:40 UTC

97 points

9 comments1 min readLW link

(worldspiritsockpuppet.com)

Spatial attention as a “tell” for empathetic simulation?

Steven Byrnes26 Apr 2024 15:10 UTC

49 points

9 comments8 min readLW link

D&D.Sci Long War: Defender of Data-mocracy

aphyer26 Apr 2024 22:30 UTC

38 points

8 comments3 min readLW link

We are headed into an extreme compute overhang

devrandom26 Apr 2024 21:38 UTC

38 points

14 comments2 min readLW link