Finding X-Risks and S-Risks by Gradient Descent

dspeyer25 Mar 2026 17:58 UTC

7 points

0 comments2 min readLW link

The Scary Bridge

moridinamael25 Mar 2026 17:11 UTC

9 points

0 comments2 min readLW link

How to do illusionist meditation

jackmastermind25 Mar 2026 17:10 UTC

4 points

0 comments11 min readLW link

Can Agents Fool Each Other? Findings from the AI Village

Shoshannah Tekofsky25 Mar 2026 17:05 UTC

12 points

1 comment3 min readLW link

(theaidigest.org)

I lost my faith in introspection—and you can too!

jackmastermind25 Mar 2026 17:00 UTC

4 points

0 comments4 min readLW link

Don’t Write Off Human Labor, Yet

burnssa25 Mar 2026 16:37 UTC

−2 points

0 comments8 min readLW link

Galaxy-brained model-chat: ASI constitutions & the cosmic host

ukc1001425 Mar 2026 16:05 UTC

11 points

0 comments16 min readLW link

How to do cost-effectiveness analysis for elections

Zach Stein-Perlman25 Mar 2026 15:00 UTC

5 points

1 comment3 min readLW link

My Cognitive Architecture: A Self-Observational Map

Naj Ami-Nave25 Mar 2026 2:23 UTC

2 points

0 comments8 min readLW link

Is Gemini 3 Scheming in the Wild?

Alejandro Wainstock, Agustin_Martinez_Suñe, Iván Arcuschin and Victor Braberman

25 Mar 2026 1:12 UTC

57 points

2 comments17 min readLW link

Book Review: Open Socrates (Part 1)

Zvi24 Mar 2026 22:21 UTC

22 points

3 comments116 min readLW link

(thezvi.wordpress.com)

Book Review: Open Socrates (Part 2)

Zvi24 Mar 2026 22:20 UTC

13 points

1 comment81 min readLW link

(thezvi.wordpress.com)

Agents Can Get Stuck in Self-distrusting Equilibria

Ashe Vazquez Nuñez24 Mar 2026 22:05 UTC

29 points

1 comment12 min readLW link

Latent Introspection (and other open-source introspection papers)

vgel24 Mar 2026 21:23 UTC

81 points

1 comment9 min readLW link

(arxiv.org)

An Informal Definition of Goals for Embedded Agents

Ashe Vazquez Nuñez24 Mar 2026 18:36 UTC

10 points

0 comments1 min readLW link

My cost-effectiveness unit

Zach Stein-Perlman24 Mar 2026 15:30 UTC

42 points

4 comments4 min readLW link

The Fourth World

Linch24 Mar 2026 13:43 UTC

19 points

14 comments6 min readLW link

Safe Recursive Self-Improvement with Verified Compilers

Adam Chlipala24 Mar 2026 13:35 UTC

10 points

0 comments11 min readLW link

Comparing Across Possible Worlds

unruly abstractions24 Mar 2026 10:09 UTC

7 points

3 comments5 min readLW link

The AIXI perspective on AI Safety

Cole Wyeth24 Mar 2026 3:24 UTC

76 points

0 comments6 min readLW link