Sorry, I still think kidney donation makes no sense for an EA

nicholashalden22 Nov 2025 18:10 UTC

−1 points

1 comment1 min readLW link

(substack.com)

Automatic alt text generation

TurnTrout22 Nov 2025 17:57 UTC

18 points

1 comment1 min readLW link

(turntrout.com)

Introspection in LLMs: A Proposal For How To Think About It, And Test For It

Christopher Ackerman22 Nov 2025 14:52 UTC

5 points

0 comments7 min readLW link

Book Review: Wizard’s Hall

Screwtape22 Nov 2025 7:38 UTC

52 points

0 comments5 min readLW link

Be Naughty

habryka22 Nov 2025 6:35 UTC

57 points

3 comments4 min readLW link

Market Logic I

abramdemski22 Nov 2025 6:01 UTC

31 points

2 comments5 min readLW link

Animal welfare concerns are dominated by post-ASI futures

RobertM22 Nov 2025 4:08 UTC

23 points

0 comments4 min readLW link

Habitual mental motions might explain why people are content to get old and die

Ruby22 Nov 2025 2:52 UTC

16 points

1 comment7 min readLW link

Diplomacy during AI takeoff

Nikola Jurkovic22 Nov 2025 2:12 UTC

15 points

3 comments2 min readLW link

(nikolajurkovic.substack.com)

Abstract advice to researchers tackling the difficult core problems of AGI alignment

TsviBT22 Nov 2025 0:53 UTC

90 points

8 comments8 min readLW link

Why Not Just Train For Interpretability?

johnswentworth21 Nov 2025 22:08 UTC

41 points

5 comments4 min readLW link

Models not making it clear when they’re roleplaying seems like a fairly big issue

williawa21 Nov 2025 20:23 UTC

16 points

0 comments6 min readLW link

Natural Emergent Misalignment from Reward Hacking

Algon21 Nov 2025 20:20 UTC

12 points

0 comments3 min readLW link

(www.anthropic.com)

Natural emergent misalignment from reward hacking in production RL

evhub, Monte M, Benjamin Wright and Jonathan Uesato

21 Nov 2025 20:00 UTC

175 points

17 comments9 min readLW link

Eight Heuristics of Anti-Epistemology

Ben Pace21 Nov 2025 19:54 UTC

21 points

2 comments6 min readLW link

We won’t solve non-alignment problems by doing research

MichaelDickens21 Nov 2025 18:03 UTC

12 points

2 comments4 min readLW link

Can Artificial Intelligence Be Conscious?

Bentham's Bulldog21 Nov 2025 16:43 UTC

12 points

3 comments7 min readLW link

Why Does Empathy Have an Off-Switch?

J Bostock21 Nov 2025 14:56 UTC

9 points

1 comment7 min readLW link

What Do We Tell the Humans? Errors, Hallucinations, and Lies in the AI Village

Shoshannah Tekofsky21 Nov 2025 14:19 UTC

42 points

0 comments8 min readLW link

Should I Apply to a 3.5% Acceptance-Rate Fellowship? A Simple EV Calculator

Tobias H21 Nov 2025 10:59 UTC

15 points

0 comments5 min readLW link