An Unintentional Compliment

abstractapplic and lsusr

28 Apr 2024 20:04 UTC

21 points

1 comment4 min readLW link

Unintentionally Creating Value

abstractapplic and lsusr

28 Apr 2024 20:05 UTC

19 points

0 comments2 min readLW link

List your AI X-Risk cruxes!

Aryeh Englander28 Apr 2024 18:26 UTC

23 points

3 comments2 min readLW link

How are Simulators and Agents related?

Robert Kralisch29 Apr 2024 0:22 UTC

4 points

0 comments7 min readLW link

The Prop-room and Stage Cognitive Architecture

Robert Kralisch29 Apr 2024 0:48 UTC

2 points

0 comments14 min readLW link

Extended Embodiment

Robert Kralisch29 Apr 2024 0:18 UTC

4 points

0 comments3 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

127 points

38 comments10 min readLW link

Referential Containment

Robert Kralisch29 Apr 2024 0:16 UTC

2 points

0 comments3 min readLW link

Disentangling Competence and Intelligence

Robert Kralisch29 Apr 2024 0:12 UTC

2 points

0 comments6 min readLW link

[Aspiration-based designs] 1. Informal introduction

B Jacobs, Jobst Heitzig, Simon Fischer and Simon Dima

28 Apr 2024 13:00 UTC

30 points

2 comments8 min readLW link

On Not Pulling The Ladder Up Behind You

Screwtape26 Apr 2024 21:58 UTC

104 points

5 comments9 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

58 points

9 comments13 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

0 comments16 min readLW link

Things I tell myself to be more agentic

DMMF28 Apr 2024 17:44 UTC

5 points

0 comments3 min readLW link

(danfrank.ca)

So What’s Up With PUFAs Chemically?

J Bostock27 Apr 2024 13:32 UTC

51 points

22 comments6 min readLW link

[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

11 points

0 comments12 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)

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

167 points

86 comments1 min readLW link