On revolutionary love in AI safety

Troy Tian22 Jun 2026 3:48 UTC

2 points

0 comments4 min readLW link

Do AI Biorisk Thresholds Need Intermediate Warning Levels?

Lukas Frei22 Jun 2026 1:09 UTC

9 points

0 comments3 min readLW link

NLA explanations can be shortened without harming reconstruction

loops22 Jun 2026 0:57 UTC

22 points

2 comments3 min readLW link

Introducing MonitoringBench

monika_j21 Jun 2026 18:43 UTC

33 points

0 comments6 min readLW link

How persona training could fail

Simon Lermen21 Jun 2026 16:38 UTC

12 points

0 comments4 min readLW link

A high-level model of AI bargaining

Anthony DiGiovanni21 Jun 2026 15:37 UTC

11 points

1 comment5 min readLW link

Policy changes should be rolled out gradually

Yair Halberstadt21 Jun 2026 11:07 UTC

24 points

2 comments3 min readLW link

A misalignment taxonomy

Alec Harris21 Jun 2026 10:20 UTC

12 points

2 comments3 min readLW link

The Cookie Monster Explains AI Safety

michaelwaves21 Jun 2026 0:52 UTC

12 points

2 comments2 min readLW link

How are there 0 studies (maybe 1) on sex-concordant hormone therapy?

Util20 Jun 2026 22:36 UTC

14 points

0 comments3 min readLW link

Against Planet-Eating Nanoreplicators

SurvivalBias20 Jun 2026 20:27 UTC

10 points

7 comments5 min readLW link

How transparent is DiffusionGemma (and why it matters)

Josh Engels, Callum McDougall, bilalchughtai, János Kramár, Senthooran Rajamanoharan, Arthur Conmy, Rohin Shah and Neel Nanda

20 Jun 2026 20:05 UTC

71 points

2 comments4 min readLW link

The Invisible Side of AI Governance

Charbel-Raphaël20 Jun 2026 18:54 UTC

94 points

4 comments14 min readLW link

Would anybody here be interested in a “mistake postmortem” discussion group?

SK220 Jun 2026 12:03 UTC

47 points

7 comments4 min readLW link

The LLM shoggoth meme is weirder than you think

HedonicEscalator19 Jun 2026 23:35 UTC

126 points

8 comments7 min readLW link

(hedonicescalator.substack.com)

How I think developers of frontier AI systems and regulators ought to act in the face of existential AI risk

WilliamKiely19 Jun 2026 22:22 UTC

12 points

0 comments12 min readLW link

Hyperstition as the Natural Enemy of Rationality

alseph19 Jun 2026 21:12 UTC

29 points

8 comments3 min readLW link

World-modeling the US vs. Anthropic Standoff on Claude Fable

dschwarz19 Jun 2026 20:04 UTC

20 points

4 comments8 min readLW link

Thoughts on Likelihood of Existential Risks by Misaligned AIs

Ishan Khire19 Jun 2026 19:17 UTC

3 points

0 comments6 min readLW link

(ishankhire.substack.com)

Why should AI be moral?

Zach Thornton19 Jun 2026 19:13 UTC

12 points

3 comments9 min readLW link