Is Bayesianism Susceptible to the Mail-Order Prophet Scam?

Max Kaye31 Mar 2026 19:30 UTC

16 points

16 comments1 min readLW link

Product Alignment is not Superintelligence Alignment (and we need the latter to survive)

plex31 Mar 2026 16:53 UTC

79 points

5 comments2 min readLW link

Experiments With Opus 4.6′s Fiction

Tomás B.31 Mar 2026 15:38 UTC

34 points

10 comments13 min readLW link

AI Safety Manual

humanityfirst31 Mar 2026 4:21 UTC

1 point

0 comments10 min readLW link

What it’s like to be an AI safety grantmaker (and why we need more of them)

Julian Hazell31 Mar 2026 3:34 UTC

1 point

0 comments11 min readLW link

(thirdthing.ai)

Arcta via est—the Narrow path out of gradual disempowerment

Founder-ArcaFutura31 Mar 2026 3:06 UTC

2 points

2 comments15 min readLW link

Your AI Travel agent would book you a bullfight: benchmarking implicit animal compassion in Agentic AI

Darkness and MilesTS

31 Mar 2026 1:34 UTC

5 points

0 comments5 min readLW link

Slack in Cells, Slack in Brains

Mateusz Bagiński31 Mar 2026 0:35 UTC

37 points

3 comments6 min readLW link

Take note of how brightness makes you feel

Adam Zerner30 Mar 2026 23:48 UTC

27 points

5 comments3 min readLW link

A Mirror Test For LLMs

Christopher Ackerman30 Mar 2026 22:44 UTC

6 points

0 comments24 min readLW link

God Can Send An Email

AlphaAndOmega30 Mar 2026 22:36 UTC

17 points

12 comments9 min readLW link

On Badness of Death

MarkelKori30 Mar 2026 20:34 UTC

0 points

1 comment3 min readLW link

How to Solve Secure Program Synthesis

Max von Hippel, Simon Henniger, Quinn Dougherty and miyazono

30 Mar 2026 20:12 UTC

19 points

0 comments11 min readLW link

Blocking live failures with synchronous monitors

Adam Kaufman and james.lucassen

30 Mar 2026 17:44 UTC

22 points

0 comments4 min readLW link

(open.substack.com)

A Guide to the Theory of Appropriateness Papers

Joel Z. Leibo30 Mar 2026 16:56 UTC

3 points

1 comment1 min readLW link

AI should be a good citizen, not just a good assistant

Tom Davidson and wdmacaskill

30 Mar 2026 14:32 UTC

37 points

11 comments9 min readLW link

(www.forethought.org)

My One-Year-Old Predictions for What the World Will Look Like in 3 Years

Ihor Kendiukhov30 Mar 2026 13:56 UTC

12 points

2 comments3 min readLW link

Propositional Alignment

williawa30 Mar 2026 13:50 UTC

5 points

0 comments2 min readLW link

The state of AI safety in four fake graphs

Boaz Barak30 Mar 2026 13:21 UTC

76 points

30 comments2 min readLW link

(Some) Natural Emergent Misalignment from Reward Hacking in Non-Production RL

7vik, Sid Black and Joseph Bloom

30 Mar 2026 10:56 UTC

105 points

3 comments17 min readLW link