On Not Pulling The Ladder Up Behind You

Screwtape26 Apr 2024 21:58 UTC

23 points

0 comments9 min readLW link

We are headed into an extreme compute overhang

devrandom26 Apr 2024 21:38 UTC

10 points

1 comment2 min readLW link

[Concept Dependency] Edge Regular Lattice Graph

Johannes C. Mayer26 Apr 2024 21:14 UTC

5 points

0 comments1 min readLW link

[Concept Dependency] Concept Dependency Posts

Johannes C. Mayer26 Apr 2024 20:57 UTC

8 points

2 comments2 min readLW link

[Question] Wouldn’t weak AI agents provide warning?

Mandatory Topic26 Apr 2024 19:34 UTC

5 points

0 comments1 min readLW link

Duct Tape security

Isaac King26 Apr 2024 18:57 UTC

31 points

0 comments5 min readLW link

Fundamental Uncertainty: Chapter 8 - When does fundamental uncertainty matter?

Gordon Seidoh Worley26 Apr 2024 18:10 UTC

8 points

1 comment32 min readLW link

Scaling of AI training runs will slow down after GPT-5

Maxime Riché26 Apr 2024 16:05 UTC

32 points

5 comments3 min readLW link

Spatial attention as a “tell” for empathetic simulation?

Steven Byrnes26 Apr 2024 15:10 UTC

41 points

5 comments8 min readLW link

Arch-anarchy

Peter lawless 26 Apr 2024 15:05 UTC

1 point

1 comment25 min readLW link

An Introduction to AI Sandbagging

Teun van der Weij, Felix Hofstätter and Francis Rhys Ward

26 Apr 2024 13:40 UTC

25 points

0 comments8 min readLW link

LLMs seem (relatively) safe

JustisMills25 Apr 2024 22:13 UTC

41 points

10 comments7 min readLW link

(justismills.substack.com)

Losing Faith In Contrarianism

omnizoid25 Apr 2024 20:53 UTC

35 points

24 comments5 min readLW link

Why I stopped being into basin broadness

tailcalled25 Apr 2024 20:47 UTC

14 points

1 comment2 min readLW link

AXRP Episode 29 - Science of Deep Learning with Vikrant Varma

DanielFilan25 Apr 2024 19:10 UTC

18 points

1 comment63 min readLW link

Improving Dictionary Learning with Gated Sparse Autoencoders

Neel Nanda, Senthooran Rajamanoharan, Arthur Conmy, lsgos, Tom Lieberum, Vikrant Varma, János Kramár and Rohin Shah

25 Apr 2024 18:43 UTC

58 points

22 comments1 min readLW link

(arxiv.org)

“Why I Write” by George Orwell (1946)

Arjun Panickssery25 Apr 2024 16:02 UTC

52 points

3 comments9 min readLW link

(www.orwellfoundation.com)

Knowledge Base 8: The truth as an attractor in the information space

iwis25 Apr 2024 15:28 UTC

−10 points

0 comments2 min readLW link

Cybersecurity of Frontier AI Models

Deric Cheng and Elliot_Mckernon

25 Apr 2024 14:51 UTC

7 points

0 comments8 min readLW link

The first future and the best future

KatjaGrace25 Apr 2024 6:40 UTC

75 points

8 comments1 min readLW link

(worldspiritsockpuppet.com)