All 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 202220232024 2025

AllJan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec

SolidGoldMagikarp (plus, prompt generation)

Jessica Rumbelow and mwatkins

5 Feb 2023 22:02 UTC

682 points

206 comments12 min readLW link 1 review

The Waluigi Effect (mega-post)

Cleo Nardo3 Mar 2023 3:22 UTC

628 points

188 comments16 min readLW link

The Talk: a brief explanation of sexual dimorphism

Malmesbury18 Sep 2023 16:23 UTC

520 points

75 comments16 min readLW link 3 reviews

How much do you believe your results?

Eric Neyman6 May 2023 20:31 UTC

507 points

18 comments15 min readLW link 4 reviews

(ericneyman.wordpress.com)

The ants and the grasshopper

Richard_Ngo4 Jun 2023 22:00 UTC

464 points

43 comments5 min readLW link 4 reviews

(www.narrativeark.xyz)

Focus on the places where you feel shocked everyone’s dropping the ball

So8res2 Feb 2023 0:27 UTC

456 points

63 comments4 min readLW link 3 reviews

Significantly Enhancing Adult Intelligence With Gene Editing May Be Possible

GeneSmith and kman

12 Dec 2023 18:14 UTC

454 points

206 comments33 min readLW link 2 reviews

Steering GPT-2-XL by adding an activation vector

TurnTrout, Monte M, David Udell, lisathiergart and Ulisse Mini

13 May 2023 18:42 UTC

437 points

98 comments50 min readLW link 1 review

Things I Learned by Spending Five Thousand Hours In Non-EA Charities

jenn1 Jun 2023 20:48 UTC

426 points

35 comments8 min readLW link 1 review

(jenn.site)

Douglas Hofstadter changes his mind on Deep Learning & AI risk (June 2023)?

gwern3 Jul 2023 0:48 UTC

426 points

54 comments7 min readLW link

(www.youtube.com)

GPTs are Predictors, not Imitators

Eliezer Yudkowsky8 Apr 2023 19:59 UTC

416 points

100 comments3 min readLW link 3 reviews

Bing Chat is blatantly, aggressively misaligned

evhub15 Feb 2023 5:29 UTC

403 points

181 comments2 min readLW link 1 review

Statement on AI Extinction—Signed by AGI Labs, Top Academics, and Many Other Notable Figures

Dan H30 May 2023 9:05 UTC

382 points

78 comments1 min readLW link 1 review

(www.safe.ai)

Please don’t throw your mind away

TsviBT15 Feb 2023 21:41 UTC

373 points

49 comments18 min readLW link 1 review

How it feels to have your mind hacked by an AI

blaked12 Jan 2023 0:33 UTC

368 points

222 comments17 min readLW link

Noting an error in Inadequate Equilibria

Matthew Barnett8 Feb 2023 1:33 UTC

366 points

60 comments2 min readLW link 2 reviews

How to have Polygenically Screened Children

GeneSmith7 May 2023 16:01 UTC

366 points

128 comments27 min readLW link 1 review

My Objections to “We’re All Gonna Die with Eliezer Yudkowsky”

Quintin Pope21 Mar 2023 0:06 UTC

359 points

233 comments39 min readLW link 1 review

Social Dark Matter

Duncan Sabien (Deactivated)16 Nov 2023 20:00 UTC

355 points

125 comments34 min readLW link 2 reviews

Shallow review of live agendas in alignment & safety

technicalities and Stag

27 Nov 2023 11:10 UTC

348 points

73 comments29 min readLW link 1 review

Fucking Goddamn Basics of Rationalist Discourse

LoganStrohl4 Feb 2023 1:47 UTC

344 points

103 comments1 min readLW link 3 reviews

Cyborgism

NicholasKees and janus

10 Feb 2023 14:47 UTC

341 points

46 comments35 min readLW link 2 reviews

Childhoods of exceptional people

Henrik Karlsson6 Feb 2023 17:27 UTC

340 points

63 comments15 min readLW link 1 review

(escapingflatland.substack.com)

Shutting Down the Lightcone Offices

habryka and Ben Pace

14 Mar 2023 22:47 UTC

338 points

103 comments17 min readLW link 2 reviews

Inside Views, Impostor Syndrome, and the Great LARP

johnswentworth25 Sep 2023 16:08 UTC

335 points

53 comments5 min readLW link

Understanding and controlling a maze-solving policy network

TurnTrout, peligrietzer, Ulisse Mini, Monte M and David Udell

11 Mar 2023 18:59 UTC

333 points

28 comments23 min readLW link

Against Almost Every Theory of Impact of Interpretability

Charbel-Raphaël17 Aug 2023 18:44 UTC

329 points

90 comments26 min readLW link 2 reviews

Sharing Information About Nonlinear

Ben Pace7 Sep 2023 6:51 UTC

323 points

323 comments34 min readLW link

Guide to rationalist interior decorating

mingyuan19 Jun 2023 6:47 UTC

320 points

49 comments12 min readLW link 4 reviews

Model Organisms of Misalignment: The Case for a New Pillar of Alignment Research

evhub, Nicholas Schiefer, Carson Denison and Ethan Perez

8 Aug 2023 1:30 UTC

318 points

30 comments18 min readLW link 1 review

EA Vegan Advocacy is not truthseeking, and it’s everyone’s problem

Elizabeth28 Sep 2023 23:30 UTC

317 points

250 comments22 min readLW link 2 reviews

(acesounderglass.com)

Alignment Grantmaking is Funding-Limited Right Now

johnswentworth19 Jul 2023 16:49 UTC

312 points

68 comments1 min readLW link

The Parable of the King and the Random Process

moridinamael1 Mar 2023 22:18 UTC

312 points

26 comments6 min readLW link 3 reviews

Book Review: How Minds Change

bc4026bd4aaa5b7fe25 May 2023 17:55 UTC

312 points

52 comments15 min readLW link

When do “brains beat brawn” in Chess? An experiment

titotal28 Jun 2023 13:33 UTC

309 points

106 comments7 min readLW link 2 reviews

(titotal.substack.com)

Speaking to Congressional staffers about AI risk

Orpheus16 and hath

4 Dec 2023 23:08 UTC

307 points

25 comments15 min readLW link 1 review

On not getting contaminated by the wrong obesity ideas

Natália28 Jan 2023 20:18 UTC

306 points

69 comments30 min readLW link

LW Team is adjusting moderation policy

Raemon4 Apr 2023 20:41 UTC

304 points

185 comments3 min readLW link

AI Timelines

habryka, Daniel Kokotajlo, Ajeya Cotra and Ege Erdil

10 Nov 2023 5:28 UTC

300 points

135 comments51 min readLW link 2 reviews

Predictable updating about AI risk

Joe Carlsmith8 May 2023 21:53 UTC

293 points

25 comments36 min readLW link 1 review

Pausing AI Developments Isn’t Enough. We Need to Shut it All Down by Eliezer Yudkowsky

jacquesthibs29 Mar 2023 23:16 UTC

291 points

297 comments3 min readLW link

(time.com)

Towards Monosemanticity: Decomposing Language Models With Dictionary Learning

Zac Hatfield-Dodds5 Oct 2023 21:01 UTC

288 points

22 comments2 min readLW link 1 review

(transformer-circuits.pub)

Accidentally Load Bearing

jefftk13 Jul 2023 16:10 UTC

287 points

18 comments1 min readLW link 1 review

(www.jefftk.com)

Hooray for stepping out of the limelight

So8res1 Apr 2023 2:45 UTC

284 points

26 comments1 min readLW link

OpenAI: The Battle of the Board

Zvi22 Nov 2023 17:30 UTC

281 points

83 comments11 min readLW link

(thezvi.wordpress.com)

Basics of Rationalist Discourse

Duncan Sabien (Deactivated)27 Jan 2023 2:40 UTC

280 points

193 comments36 min readLW link 4 reviews

The 6D effect: When companies take risks, one email can be very powerful.

scasper4 Nov 2023 20:08 UTC

278 points

42 comments3 min readLW link

Notes on Teaching in Prison

jsd19 Apr 2023 1:53 UTC

274 points

13 comments12 min readLW link

We don’t trade with ants

KatjaGrace10 Jan 2023 23:50 UTC

271 points

109 comments7 min readLW link 1 review

(worldspiritsockpuppet.com)

OpenAI: Facts from a Weekend

Zvi20 Nov 2023 15:30 UTC

271 points

165 comments9 min readLW link

(thezvi.wordpress.com)