There are no coherence theorems

20 Feb 2023 21:25 UTC

128 points

123 comments19 min readLW link

Universal Basic Income and Poverty

Eliezer Yudkowsky26 Jul 2024 7:23 UTC

113 points

38 comments9 min readLW link

“AI achieves silver-medal standard solving International Mathematical Olympiad problems”

gjm25 Jul 2024 15:58 UTC

112 points

33 comments2 min readLW link

(deepmind.google)

The Best Tacit Knowledge Videos on Every Subject

Parker Conley31 Mar 2024 17:14 UTC

347 points

138 comments16 min readLW link

Me, Myself, and AI: the Situational Awareness Dataset (SAD) for LLMs

L Rudolf L, bilalchughtai, jan betley, kaivu, Jérémy Scheurer, Mikita Balesni, AlexMeinke, Owain_Evans and Marius Hobbhahn

8 Jul 2024 22:24 UTC

99 points

27 comments5 min readLW link

Beyond Kolmogorov and Shannon

Alexander Gietelink Oldenziel and Adam Shai

25 Oct 2022 15:13 UTC

62 points

19 comments5 min readLW link

Efficient Dictionary Learning with Switch Sparse Autoencoders

Anish Mudide22 Jul 2024 18:45 UTC

94 points

15 comments12 min readLW link

A Visual Task that’s Hard for GPT-4o, but Doable for Primary Schoolers

Lennart Finke26 Jul 2024 17:51 UTC

6 points

1 comment2 min readLW link

[Question] Are there any naturally occurring heat pumps?

FactorialCode13 Apr 2020 5:24 UTC

17 points

11 comments1 min readLW link

Pacing Outside the Box: RNNs Learn to Plan in Sokoban

Adrià Garriga-alonso, taufeeque, AdamGleave and ChengCheng

25 Jul 2024 22:00 UTC

47 points

4 comments2 min readLW link

(arxiv.org)

The case for stopping AI safety research

catubc23 May 2024 15:55 UTC

51 points

36 comments1 min readLW link

What does a Gambler’s Verity world look like?

ErioirE25 Jul 2024 22:03 UTC

5 points

2 comments1 min readLW link

The Cancer Resolution?

PeterMcCluskey24 Jul 2024 0:25 UTC

14 points

20 comments6 min readLW link

(bayesianinvestor.com)

Constructing Benchmarks and Interventions for Combating Hallucinations in LLMs

Adi Simhi25 Jul 2024 14:58 UTC

−5 points

3 comments6 min readLW link

End Single Family Zoning by Overturning Euclid V Ambler

Maxwell Tabarrok26 Jul 2024 14:08 UTC

30 points

1 comment7 min readLW link

(www.maximum-progress.com)

Positive visions for AI

L Rudolf L and Florence Hinder

23 Jul 2024 20:15 UTC

26 points

4 comments18 min readLW link

(www.florencehinder.com)

I bet $500 on AI winning the IMO gold medal by 2026

azsantosk11 May 2023 14:46 UTC

37 points

29 comments1 min readLW link

Unaligned AI is coming regardless.

verbalshadow26 Jul 2024 16:41 UTC

−14 points

0 comments2 min readLW link

Confusing the metric for the meaning: Perhaps correlated attributes are “natural”

NickyP23 Jul 2024 12:43 UTC

31 points

3 comments4 min readLW link

I would have shit in that alley, too

Declan Molony18 Jun 2024 4:41 UTC

398 points

128 comments4 min readLW link