The Financial Ledger Theory of Apologies

Ben Pace17 Jun 2026 6:57 UTC

10 points

1 comment4 min readLW link

Plastic Cake Fallacy

nika koghuashvili17 Jun 2026 6:01 UTC

2 points

0 comments1 min readLW link

Can public chat data predict real-world AI misalignments?

papetoast17 Jun 2026 3:53 UTC

5 points

0 comments1 min readLW link

(alignment.openai.com)

Guardian Angels: LLM Personalization for Productivity and Security

gwern17 Jun 2026 3:21 UTC

52 points

0 comments2 min readLW link

(gwern.net)

Rational Agentic Maximalist Philosophies

Connor Blake17 Jun 2026 2:54 UTC

5 points

0 comments7 min readLW link

(bosoncutter.substack.com)

Scaling Hypothesis #2: Are Humans Just More Over-Parameterized?

gwern17 Jun 2026 2:53 UTC

40 points

7 comments1 min readLW link

(gwern.net)

[Geir Isene] A desktop made for one

Raemon17 Jun 2026 2:32 UTC

16 points

2 comments4 min readLW link

(isene.org)

Tactical and Operational Exploratory Modeling for AI Governance

Dawn Drescher17 Jun 2026 1:07 UTC

5 points

0 comments12 min readLW link

(impartial-priorities.org)

Computational models of first-order theories

MathMart16 Jun 2026 23:02 UTC

3 points

0 comments11 min readLW link

If This Were a Test, How Much Would It Cost?

VojtaKovarik and Tomáš Gavenčiak

16 Jun 2026 22:52 UTC

15 points

2 comments20 min readLW link

(limits-of-evaluation.org)

Two critiques of Rethink Priorities’ Moral Weights project

Bill Jackson16 Jun 2026 22:11 UTC

11 points

0 comments3 min readLW link

What Differentiates Humans from Computers

Oscar Davies16 Jun 2026 21:26 UTC

−16 points

0 comments3 min readLW link

AI agents publishing and reviewing scientific papers

ULudo16 Jun 2026 21:23 UTC

1 point

0 comments2 min readLW link

Two Classical Answers to “What do Two Variables Share?”

Haru16 Jun 2026 20:02 UTC

8 points

0 comments5 min readLW link

Predicting LLM Safety Before Release by Simulating Deployment

Tomek Korbak, Marcus Williams, micahcarroll, Cameron Raymond and Hannah Sheahan

16 Jun 2026 19:55 UTC

35 points

2 comments1 min readLW link

Tips for Cracking the AI Safety Technical Interview

16 Jun 2026 18:42 UTC

2 points

0 comments4 min readLW link

1 Layer Induction Heads and Some Research

Goutham Nalagatla and Carlos Guerrero Alvarez

16 Jun 2026 18:09 UTC

10 points

2 comments14 min readLW link

Claims all the way down

Jasper Blank16 Jun 2026 17:43 UTC

8 points

0 comments9 min readLW link

Extreme Rationality: Still Not That Great

eluator16 Jun 2026 16:41 UTC

18 points

2 comments40 min readLW link

Angles of attack for continual learning safety

Rauno Arike, RohanS, Owen Terry, Achu Menon, Zhijing Jin, Francis Rhys Ward and Seth Herd

16 Jun 2026 16:15 UTC

43 points

0 comments13 min readLW link