There is no evidence you should reapply sunscreen every 2 hours.

Hide6 May 2026 9:19 UTC

11 points

0 comments9 min readLW link

(hidefromit.substack.com)

Building An Ancestor Simulation #2

Mira Kennard6 May 2026 8:21 UTC

4 points

0 comments5 min readLW link

Psychopathy: The Types

Dawn Drescher6 May 2026 7:35 UTC

2 points

0 comments10 min readLW link

(impartial-priorities.org)

ACX Montreal meetup—May 9thh @2PM

nik lacombe6 May 2026 4:51 UTC

4 points

0 comments1 min readLW link

Toward a Better Evaluations Ecosystem

Benjamin Arnav5 May 2026 22:29 UTC

14 points

0 comments5 min readLW link

LW-Cologne meetup

EGI5 May 2026 22:24 UTC

5 points

0 comments1 min readLW link

Model Spec Midtraining: Improving How Alignment Training Generalizes

Chloe Li, saraprice, Sam Marks and Jonathan Kutasov

5 May 2026 21:55 UTC

50 points

0 comments7 min readLW link

Positive Feedback Only

Florian_Dietz5 May 2026 21:28 UTC

16 points

0 comments8 min readLW link

What if LLMs are mostly crystallized intelligence?

deep5 May 2026 20:50 UTC

26 points

3 comments9 min readLW link

(expectedsurprise.substack.com)

Decision theory doesn’t prove that useful strong AIs will doom us all

deep5 May 2026 20:47 UTC

4 points

0 comments9 min readLW link

(expectedsurprise.substack.com)

Psychopathy: The Mechanics

Dawn Drescher5 May 2026 20:26 UTC

5 points

0 comments10 min readLW link

(impartial-priorities.org)

A Federal Inmate Asks: Was My Prosecution Rational?

seth_tins5 May 2026 19:56 UTC

1 point

2 comments5 min readLW link

The AI Ad-Hoc Prior Restraint Era Begins

Zvi5 May 2026 19:30 UTC

54 points

3 comments10 min readLW link

(thezvi.wordpress.com)

Your rights when flying to Europe

Yair Halberstadt5 May 2026 19:17 UTC

72 points

6 comments5 min readLW link

[Linkpost] Interpreting Language Model Parameters

Lucius Bushnaq, Dan Braun, Oliver Clive-Griffin, Bart Bussmann, Nathan Hu, mivanitskiy, Linda Linsefors and Lee Sharkey

5 May 2026 17:37 UTC

114 points

2 comments2 min readLW link

(www.goodfire.ai)

Motivated reasoning, confirmation bias, and AI risk theory

Seth Herd5 May 2026 15:56 UTC

40 points

8 comments41 min readLW link

The Best Argument Against Deontology Is About Suitcases

Bentham's Bulldog5 May 2026 15:24 UTC

−4 points

7 comments19 min readLW link

Codesign for Legibility (to AI and Everyone Else)

Adam Chlipala5 May 2026 13:46 UTC

1 point

0 comments7 min readLW link

Dawn of the “national security” tier of AI

Mitchell_Porter5 May 2026 9:40 UTC

14 points

2 comments1 min readLW link

Forbidden Backrooms: Self-Chat with a Refusal-Abliterated LLM

AlliedToasters5 May 2026 7:55 UTC

8 points

0 comments5 min readLW link