Eliezer Yudkowsky

Karma: 159,342

Contradict my take on OpenPhil’s past AI beliefs

Eliezer Yudkowsky20 Dec 2025 21:15 UTC

195 points

92 comments3 min readLW link

Eliezer’s Unteachable Methods of Sanity

Eliezer Yudkowsky7 Dec 2025 2:46 UTC

492 points

152 comments10 min readLW link

The Tale of the Top-Tier Intellect

Eliezer Yudkowsky3 Nov 2025 20:21 UTC

105 points

58 comments35 min readLW link

On Fleshling Safety: A Debate by Klurl and Trapaucius.

Eliezer Yudkowsky26 Oct 2025 23:44 UTC

257 points

52 comments79 min readLW link

Why Corrigibility is Hard and Important (i.e. “Whence the high MIRI confidence in alignment difficulty?”)

Raemon, Eliezer Yudkowsky and So8res

30 Sep 2025 0:12 UTC

95 points

58 comments17 min readLW link

Re: recent Anthropic safety research

Eliezer Yudkowsky6 Aug 2025 22:52 UTC

153 points

24 comments5 min readLW link

(x.com)

The Problem

Rob Bensinger, tanagrabeast, yams, So8res, Eliezer Yudkowsky and Gretta Duleba

5 Aug 2025 21:40 UTC

324 points

217 comments26 min readLW link

HPMOR: The (Probably) Untold Lore

Gretta Duleba and Eliezer Yudkowsky

25 Jul 2025 18:39 UTC

428 points

164 comments38 min readLW link

The Sun is big, but superintelligences will not spare Earth a little sunlight

Eliezer Yudkowsky23 Sep 2024 3:39 UTC

217 points

143 comments13 min readLW link

Universal Basic Income and Poverty

Eliezer Yudkowsky26 Jul 2024 7:23 UTC

357 points

150 comments9 min readLW link 1 review

‘Empiricism!’ as Anti-Epistemology

Eliezer Yudkowsky14 Mar 2024 2:02 UTC

172 points

96 comments25 min readLW link 1 review

My current LK99 questions

Eliezer Yudkowsky1 Aug 2023 22:48 UTC

210 points

38 comments5 min readLW link

GPTs are Predictors, not Imitators

Eliezer Yudkowsky8 Apr 2023 19:59 UTC

428 points

100 comments3 min readLW link 3 reviews

Pausing AI Developments Isn’t Enough. We Need to Shut it All Down

Eliezer Yudkowsky8 Apr 2023 0:36 UTC

270 points

44 comments12 min readLW link 1 review

Eliezer Yudkowsky’s Shortform

Eliezer Yudkowsky1 Apr 2023 22:43 UTC

14 points

0 comments1 min readLW link

Manifold: If okay AGI, why?

Eliezer Yudkowsky25 Mar 2023 22:43 UTC

121 points

37 comments1 min readLW link

(manifold.markets)

Alexander and Yudkowsky on AGI goals

Scott Alexander and Eliezer Yudkowsky

24 Jan 2023 21:09 UTC

179 points

53 comments26 min readLW link 1 review

A challenge for AGI organizations, and a challenge for readers

Rob Bensinger and Eliezer Yudkowsky

1 Dec 2022 23:11 UTC

303 points

33 comments2 min readLW link

Don’t use ‘infohazard’ for collectively destructive info

Eliezer Yudkowsky15 Jul 2022 5:13 UTC

87 points

34 comments1 min readLW link 2 reviews

(www.facebook.com)

Let’s See You Write That Corrigibility Tag

Eliezer Yudkowsky19 Jun 2022 21:11 UTC

124 points

70 comments1 min readLW link