The behavioral selection model for predicting AI motivations

Alex Mallen and Buck

4 Dec 2025 18:46 UTC

137 points

13 comments16 min readLW link

Why people like your quick bullshit takes better than your high-effort posts

eukaryote28 Nov 2025 20:12 UTC

221 points

27 comments5 min readLW link

(eukaryotewritesblog.com)

Alignment remains a hard, unsolved problem

evhub27 Nov 2025 8:45 UTC

337 points

94 comments14 min readLW link

Natural emergent misalignment from reward hacking in production RL

evhub, Monte M, Benjamin Wright and Jonathan Uesato

21 Nov 2025 20:00 UTC

258 points

32 comments9 min readLW link

How Colds Spread

RobertM18 Nov 2025 5:25 UTC

233 points

28 comments10 min readLW link

Paranoia: A Beginner’s Guide

habryka13 Nov 2025 7:56 UTC

333 points

70 comments13 min readLW link

Legible vs. Illegible AI Safety Problems

Wei Dai4 Nov 2025 21:39 UTC

361 points

93 comments2 min readLW link

The Unreasonable Effectiveness of Fiction

Raelifin3 Nov 2025 15:35 UTC

208 points

26 comments8 min readLW link

(raelifin.substack.com)

Human Values ≠ Goodness

johnswentworth2 Nov 2025 19:24 UTC

38 points

74 comments6 min readLW link

LLM-generated text is not testimony

TsviBT1 Nov 2025 14:47 UTC

104 points

86 comments11 min readLW link

The Memetics of AI Successionism

Jan_Kulveit28 Oct 2025 15:04 UTC

212 points

54 comments9 min readLW link

Cancer has a surprising amount of detail

Abhishaike Mahajan26 Oct 2025 20:33 UTC

127 points

18 comments11 min readLW link

(www.owlposting.com)

EU explained in 10 minutes

Martin Sustrik21 Oct 2025 4:40 UTC

244 points

49 comments8 min readLW link

(www.250bpm.com)

The “Length” of “Horizons”

Adam Scholl14 Oct 2025 14:48 UTC

183 points

27 comments7 min readLW link

The Most Common Bad Argument In These Parts

J Bostock11 Oct 2025 16:29 UTC

242 points

60 comments4 min readLW link

Towards a Typology of Strange LLM Chains-of-Thought

1a3orn9 Oct 2025 22:02 UTC

301 points

29 comments9 min readLW link

Do One New Thing A Day To Solve Your Problems

Algon3 Oct 2025 17:08 UTC

208 points

28 comments2 min readLW link

Ethical Design Patterns

AnnaSalamon30 Sep 2025 11:52 UTC

227 points

49 comments20 min readLW link

Notes on fatalities from AI takeover

ryan_greenblatt23 Sep 2025 17:18 UTC

56 points

61 comments8 min readLW link

The Company Man

Tomás B.17 Sep 2025 17:47 UTC

771 points

74 comments18 min readLW link