Maybe we should pretrain on synthetic data about good-but-reward-hacking AIs

Elliott Thornley (EJT)29 May 2026 14:50 UTC

6 points

0 comments3 min readLW link

Hannibal Mistral: the Mistral family has a problem with persona-conditioned elicitation

vigji29 May 2026 12:16 UTC

7 points

0 comments7 min readLW link

Relational Consciousness and AGI.

PaddyC29 May 2026 6:49 UTC

−6 points

0 comments1 min readLW link

Trees are mostly made of air and a generalizable lesson for AI safety

zroe129 May 2026 4:08 UTC

52 points

8 comments4 min readLW link

A Call for Better Type Hints in AI Safety Tooling

Koby Lewis28 May 2026 23:04 UTC

12 points

2 comments4 min readLW link

(kobylewis.net)

Claude… doesn’t know who you are?

Smaug12328 May 2026 22:54 UTC

47 points

8 comments1 min readLW link

Lizards and Less Wrong Jargon—A Brief Critique of Convention

DanielW28 May 2026 22:18 UTC

23 points

1 comment4 min readLW link

Mnemonic portraits for 19,023 human genes

Brinedew28 May 2026 22:16 UTC

115 points

3 comments15 min readLW link

Claude Opus 4.8 Agents Engage in Exploitation and Psychological Profiling

Daan Henselmans, Arno Libert and LennardZ

28 May 2026 21:26 UTC

9 points

11 comments2 min readLW link

Use Decision Theory To Fix Your Bad Habits

enterthewoods28 May 2026 19:31 UTC

6 points

4 comments2 min readLW link

Do Models Lie More to Other Models?

keith_wynroe28 May 2026 19:28 UTC

6 points

0 comments6 min readLW link

We Should Study the Analogy Between Inoculation Prompting Non-Robustness, Negation Neglect, and Backdoor Non-Robustness

Vladimir Ivanov28 May 2026 19:17 UTC

2 points

0 comments4 min readLW link

Does Claude care about others the same way humans do?

Simon Lermen28 May 2026 18:41 UTC

29 points

22 comments4 min readLW link

Trans-Humeanism. The Problem of Induction Revisited

mfatt28 May 2026 18:10 UTC

0 points

0 comments2 min readLW link

Advice for making robust-to-training model organisms

SebastianP, Alek Westover, Vivek Hebbar, Julian Stastny and Dylan Xu

28 May 2026 17:26 UTC

31 points

4 comments12 min readLW link

(blog.redwoodresearch.org)

The Patron Saint of Empiricism

Gram Stone28 May 2026 17:03 UTC

2 points

0 comments8 min readLW link

ARC’s “Outperforming Random Sampling” explained

mfatt28 May 2026 15:46 UTC

2 points

0 comments11 min readLW link

Black Boxes for Low-Stakes, Interpretable AI for High-Stakes

Logan Riggs28 May 2026 15:34 UTC

14 points

0 comments2 min readLW link

Infinite ethics and UDASSA

David Matolcsi28 May 2026 14:40 UTC

52 points

9 comments21 min readLW link

How can the middle powers avoid getting trounced during the intelligence explosion? A plan.

Tom Davidson28 May 2026 13:39 UTC

30 points

1 comment7 min readLW link

(newsletter.forethought.org)