All 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 20232024

AllJan Feb Mar Apr May Jun Jul

LessWrong’s (first) album: I Have Been A Good Bing

habryka and kave

1 Apr 2024 7:33 UTC

556 points

173 comments11 min readLW link

I would have shit in that alley, too

Declan Molony18 Jun 2024 4:41 UTC

398 points

128 comments4 min readLW link

Transformers Represent Belief State Geometry in their Residual Stream

Adam Shai16 Apr 2024 21:16 UTC

397 points

100 comments12 min readLW link

There is way too much serendipity

Malmesbury19 Jan 2024 19:37 UTC

357 points

56 comments7 min readLW link

Failures in Kindness

silentbob26 Mar 2024 21:30 UTC

354 points

48 comments9 min readLW link

My hour of memoryless lucidity

Eric Neyman4 May 2024 1:40 UTC

349 points

34 comments5 min readLW link

(ericneyman.wordpress.com)

The Best Tacit Knowledge Videos on Every Subject

Parker Conley31 Mar 2024 17:14 UTC

347 points

138 comments16 min readLW link

Thoughts on seed oil

dynomight20 Apr 2024 12:29 UTC

341 points

122 comments17 min readLW link

(dynomight.net)

Reliable Sources: The Story of David Gerard

TracingWoodgrains10 Jul 2024 19:50 UTC

333 points

52 comments43 min readLW link

Notifications Received in 30 Minutes of Class

tanagrabeast26 May 2024 17:02 UTC

332 points

11 comments8 min readLW link

[April Fools’ Day] Introducing Open Asteroid Impact

Linch1 Apr 2024 8:14 UTC

332 points

29 comments1 min readLW link

(openasteroidimpact.org)

Safety isn’t safety without a social model (or: dispelling the myth of per se technical safety)

Andrew_Critch14 Jun 2024 0:16 UTC

324 points

34 comments4 min readLW link

MIRI 2024 Communications Strategy

Gretta Duleba29 May 2024 19:33 UTC

318 points

198 comments7 min readLW link

Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

evhub, Carson Denison, Meg, Monte M, David Duvenaud, Nicholas Schiefer and Ethan Perez

12 Jan 2024 19:51 UTC

299 points

95 comments3 min readLW link

(arxiv.org)

Non-Disparagement Canaries for OpenAI

aysja and Adam Scholl

30 May 2024 19:20 UTC

287 points

51 comments2 min readLW link

Gentleness and the artificial Other

Joe Carlsmith2 Jan 2024 18:21 UTC

282 points

33 comments11 min readLW link

Scale Was All We Needed, At First

Gabe M14 Feb 2024 1:49 UTC

277 points

32 comments8 min readLW link

(aiacumen.substack.com)

My AI Model Delta Compared To Yudkowsky

johnswentworth10 Jun 2024 16:12 UTC

272 points

100 comments4 min readLW link

80,000 hours should remove OpenAI from the Job Board (and similar EA orgs should do similarly)

Raemon3 Jul 2024 20:34 UTC

268 points

63 comments1 min readLW link

Express interest in an “FHI of the West”

habryka18 Apr 2024 3:32 UTC

264 points

41 comments3 min readLW link

On green

Joe Carlsmith21 Mar 2024 17:38 UTC

261 points

35 comments31 min readLW link

Getting 50% (SoTA) on ARC-AGI with GPT-4o

ryan_greenblatt17 Jun 2024 18:44 UTC

257 points

49 comments13 min readLW link

Paul Christiano named as US AI Safety Institute Head of AI Safety

Joel Burget16 Apr 2024 16:22 UTC

256 points

59 comments1 min readLW link

(www.commerce.gov)

“No-one in my org puts money in their pension”

Tobes16 Feb 2024 18:33 UTC

253 points

16 comments9 min readLW link

(seekingtobejolly.substack.com)

My PhD thesis: Algorithmic Bayesian Epistemology

Eric Neyman16 Mar 2024 22:56 UTC

252 points

14 comments7 min readLW link

(arxiv.org)

The case for ensuring that powerful AIs are controlled

ryan_greenblatt and Buck

24 Jan 2024 16:11 UTC

250 points

66 comments28 min readLW link

Ilya Sutskever and Jan Leike resign from OpenAI [updated]

Zach Stein-Perlman15 May 2024 0:45 UTC

246 points

95 comments2 min readLW link

AI companies aren’t really using external evaluators

Zach Stein-Perlman24 May 2024 16:01 UTC

240 points

15 comments4 min readLW link

My Clients, The Liars

ymeskhout5 Mar 2024 21:06 UTC

238 points

85 comments7 min readLW link

Refusal in LLMs is mediated by a single direction

Andy Arditi, Oscar Obeso, Aaquib111, wesg and Neel Nanda

27 Apr 2024 11:13 UTC

222 points

87 comments10 min readLW link

Introducing AI Lab Watch

Zach Stein-Perlman30 Apr 2024 17:00 UTC

222 points

30 comments1 min readLW link

(ailabwatch.org)

MIRI 2024 Mission and Strategy Update

Malo5 Jan 2024 0:20 UTC

221 points

44 comments8 min readLW link

Modern Transformers are AGI, and Human-Level

abramdemski26 Mar 2024 17:46 UTC

219 points

89 comments5 min readLW link

SAE feature geometry is outside the superposition hypothesis

jake_mendel24 Jun 2024 16:07 UTC

216 points

17 comments11 min readLW link

Believing In

AnnaSalamon8 Feb 2024 7:06 UTC

215 points

50 comments13 min readLW link

CFAR Takeaways: Andrew Critch

Raemon14 Feb 2024 1:37 UTC

215 points

62 comments5 min readLW link

Brute Force Manufactured Consensus is Hiding the Crime of the Century

Roko3 Feb 2024 20:36 UTC

214 points

156 comments9 min readLW link

ChatGPT can learn indirect control

Raymond D21 Mar 2024 21:11 UTC

213 points

24 comments1 min readLW link

Truthseeking is the ground in which other principles grow

Elizabeth27 May 2024 1:09 UTC

207 points

14 comments16 min readLW link

“How could I have thought that faster?”

mesaoptimizer11 Mar 2024 10:56 UTC

205 points

32 comments2 min readLW link

(twitter.com)

OpenAI: Fallout

Zvi28 May 2024 13:20 UTC

204 points

25 comments36 min readLW link

(thezvi.wordpress.com)

Raising children on the eve of AI

juliawise15 Feb 2024 21:28 UTC

204 points

38 comments5 min readLW link

Towards more cooperative AI safety strategies

Richard_Ngo16 Jul 2024 4:36 UTC

202 points

126 comments4 min readLW link

LLM Generality is a Timeline Crux

eggsyntax24 Jun 2024 12:52 UTC

201 points

92 comments7 min readLW link

Superbabies: Putting The Pieces Together

sarahconstantin11 Jul 2024 20:40 UTC

200 points

35 comments10 min readLW link

(sarahconstantin.substack.com)

Jaan Tallinn’s 2023 Philanthropy Overview

jaan20 May 2024 12:11 UTC

199 points

5 comments1 min readLW link

(jaan.info)

Maybe Anthropic’s Long-Term Benefit Trust is powerless

Zach Stein-Perlman27 May 2024 13:00 UTC

199 points

21 comments2 min readLW link

Mechanistically Eliciting Latent Behaviors in Language Models

Andrew Mack and TurnTrout

30 Apr 2024 18:51 UTC

199 points

37 comments45 min readLW link

Sam Altman’s Chip Ambitions Undercut OpenAI’s Safety Strategy

garrison10 Feb 2024 19:52 UTC

198 points

52 comments1 min readLW link

(garrisonlovely.substack.com)

Funny Anecdote of Eliezer From His Sister

Noah Birnbaum22 Apr 2024 22:05 UTC

195 points

6 comments2 min readLW link