Why we are excited about confession!

Boaz Barak, Gabriel Wu and Manas Joglekar

14 Jan 2026 20:37 UTC

119 points

27 comments9 min readLW link

(alignment.openai.com)

In My Misanthropy Era

jenn4 Jan 2026 18:34 UTC

314 points

142 comments8 min readLW link

(jenn.site)

2025 in AI predictions

jessicata2 Jan 2026 4:29 UTC

233 points

19 comments11 min readLW link

Turning 20 in the probable pre-apocalypse

Parv Mahajan21 Dec 2025 10:14 UTC

386 points

61 comments3 min readLW link

Eliezer’s Unteachable Methods of Sanity

Eliezer Yudkowsky7 Dec 2025 2:46 UTC

479 points

147 comments10 min readLW link

Measuring no CoT math time horizon (single forward pass)

ryan_greenblatt26 Dec 2025 16:37 UTC

212 points

18 comments3 min readLW link

Opinionated Takes on Meetups Organizing

jenn20 Dec 2025 0:17 UTC

246 points

34 comments9 min readLW link

6 reasons why “alignment-is-hard” discourse seems alien to human intuitions, and vice-versa

Steven Byrnes3 Dec 2025 18:37 UTC

352 points

87 comments17 min readLW link

Alignment remains a hard, unsolved problem

evhub27 Nov 2025 8:45 UTC

361 points

96 comments14 min readLW link

How I stopped being sure LLMs are just making up their internal experience (but the topic is still confusing)

Kaj_Sotala13 Dec 2025 12:38 UTC

198 points

66 comments29 min readLW link

The Company Man

Tomás B.17 Sep 2025 17:47 UTC

784 points

79 comments18 min readLW link

Insights into Claude Opus 4.5 from Pokémon

Julian Bradshaw9 Dec 2025 16:57 UTC

204 points

24 comments10 min readLW link

Paranoia: A Beginner’s Guide

habryka13 Nov 2025 7:56 UTC

343 points

70 comments13 min readLW link

The Rise of Parasitic AI

Adele Lopez11 Sep 2025 4:38 UTC

716 points

179 comments20 min readLW link

Legible vs. Illegible AI Safety Problems

Wei Dai4 Nov 2025 21:39 UTC

365 points

93 comments2 min readLW link

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

eukaryote28 Nov 2025 20:12 UTC

227 points

27 comments5 min readLW link

(eukaryotewritesblog.com)

Natural emergent misalignment from reward hacking in production RL

evhub, Monte M, Benjamin Wright and Jonathan Uesato

21 Nov 2025 20:00 UTC

261 points

32 comments9 min readLW link

The behavioral selection model for predicting AI motivations

Alex Mallen and Buck

4 Dec 2025 18:46 UTC

181 points

27 comments16 min readLW link

Good if make prior after data instead of before

dynomight18 Dec 2025 17:53 UTC

114 points

15 comments9 min readLW link

(dynomight.net)

How Colds Spread

RobertM18 Nov 2025 5:25 UTC

239 points

31 comments10 min readLW link