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

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

676 points

205 comments12 min readLW link

The Waluigi Effect (mega-post)

Cleo Nardo3 Mar 2023 3:22 UTC

628 points

187 comments16 min readLW link

The Talk: a brief explanation of sexual dimorphism

Malmesbury18 Sep 2023 16:23 UTC

492 points

72 comments16 min readLW link

How much do you believe your results?

Eric Neyman6 May 2023 20:31 UTC

467 points

14 comments15 min readLW link

(ericneyman.wordpress.com)

Significantly Enhancing Adult Intelligence With Gene Editing May Be Possible

GeneSmith and kman

12 Dec 2023 18:14 UTC

451 points

168 comments33 min readLW link

Steering GPT-2-XL by adding an activation vector

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

13 May 2023 18:42 UTC

436 points

97 comments50 min readLW link

The ants and the grasshopper

Richard_Ngo4 Jun 2023 22:00 UTC

428 points

35 comments5 min readLW link

(www.narrativeark.xyz)

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

gwern3 Jul 2023 0:48 UTC

425 points

54 comments7 min readLW link

(www.youtube.com)

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

So8res2 Feb 2023 0:27 UTC

421 points

60 comments4 min readLW link

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

jenn1 Jun 2023 20:48 UTC

414 points

34 comments8 min readLW link

(jenn.site)

GPTs are Predictors, not Imitators

Eliezer Yudkowsky8 Apr 2023 19:59 UTC

403 points

91 comments3 min readLW link

Bing Chat is blatantly, aggressively misaligned

evhub15 Feb 2023 5:29 UTC

400 points

180 comments2 min readLW link

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

Dan H30 May 2023 9:05 UTC

370 points

77 comments1 min readLW link

(www.safe.ai)

Noting an error in Inadequate Equilibria

Matthew Barnett8 Feb 2023 1:33 UTC

361 points

56 comments2 min readLW link

How it feels to have your mind hacked by an AI

blaked12 Jan 2023 0:33 UTC

361 points

221 comments17 min readLW link

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

Quintin Pope21 Mar 2023 0:06 UTC

357 points

230 comments39 min readLW link

How to have Polygenically Screened Children

GeneSmith7 May 2023 16:01 UTC

354 points

127 comments27 min readLW link

Please don’t throw your mind away

TsviBT15 Feb 2023 21:41 UTC

341 points

44 comments18 min readLW link

Shutting Down the Lightcone Offices

habryka and Ben Pace

14 Mar 2023 22:47 UTC

338 points

95 comments17 min readLW link

Cyborgism

NicholasKees and janus

10 Feb 2023 14:47 UTC

336 points

46 comments35 min readLW link

Inside Views, Impostor Syndrome, and the Great LARP

johnswentworth25 Sep 2023 16:08 UTC

331 points

53 comments5 min readLW link

Childhoods of exceptional people

Henrik Karlsson6 Feb 2023 17:27 UTC

330 points

62 comments15 min readLW link

(escapingflatland.substack.com)

Understanding and controlling a maze-solving policy network

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

11 Mar 2023 18:59 UTC

328 points

27 comments23 min readLW link

Shallow review of live agendas in alignment & safety

technicalities and Stag

27 Nov 2023 11:10 UTC

322 points

69 comments29 min readLW link

Against Almost Every Theory of Impact of Interpretability

Charbel-Raphaël17 Aug 2023 18:44 UTC

322 points

86 comments26 min readLW link

Sharing Information About Nonlinear

Ben Pace7 Sep 2023 6:51 UTC

322 points

323 comments34 min readLW link

Fucking Goddamn Basics of Rationalist Discourse

LoganStrohl4 Feb 2023 1:47 UTC

319 points

100 comments1 min readLW link

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

Elizabeth28 Sep 2023 23:30 UTC

317 points

247 comments22 min readLW link

(acesounderglass.com)

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

312 points

28 comments18 min readLW link

Alignment Grantmaking is Funding-Limited Right Now

johnswentworth19 Jul 2023 16:49 UTC

312 points

68 comments1 min readLW link

On not getting contaminated by the wrong obesity ideas

Natália28 Jan 2023 20:18 UTC

311 points

68 comments30 min readLW link

Social Dark Matter

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

311 points

115 comments34 min readLW link

Book Review: How Minds Change

bc4026bd4aaa5b7fe25 May 2023 17:55 UTC

309 points

52 comments15 min readLW link

LW Team is adjusting moderation policy

Raemon4 Apr 2023 20:41 UTC

304 points

185 comments3 min readLW link

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

titotal28 Jun 2023 13:33 UTC

303 points

82 comments7 min readLW link

(titotal.substack.com)

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

jacquesthibs29 Mar 2023 23:16 UTC

298 points

297 comments3 min readLW link

(time.com)

Speaking to Congressional staffers about AI risk

Akash and hath

4 Dec 2023 23:08 UTC

297 points

23 comments16 min readLW link

Guide to rationalist interior decorating

mingyuan19 Jun 2023 6:47 UTC

296 points

45 comments12 min readLW link

The Parable of the King and the Random Process

moridinamael1 Mar 2023 22:18 UTC

294 points

23 comments6 min readLW link

Predictable updating about AI risk

Joe Carlsmith8 May 2023 21:53 UTC

288 points

24 comments36 min readLW link

Towards Monosemanticity: Decomposing Language Models With Dictionary Learning

Zac Hatfield-Dodds5 Oct 2023 21:01 UTC

287 points

21 comments2 min readLW link

(transformer-circuits.pub)

Hooray for stepping out of the limelight

So8res1 Apr 2023 2:45 UTC

282 points

24 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)

AI Timelines

habryka, Daniel Kokotajlo, Ajeya Cotra and Ege Erdil

10 Nov 2023 5:28 UTC

279 points

96 comments51 min readLW link

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

scasper4 Nov 2023 20:08 UTC

275 points

42 comments3 min readLW link

Notes on Teaching in Prison

jsd19 Apr 2023 1:53 UTC

274 points

13 comments12 min readLW link

Accidentally Load Bearing

jefftk13 Jul 2023 16:10 UTC

273 points

15 comments1 min readLW link

(www.jefftk.com)

OpenAI: Facts from a Weekend

Zvi20 Nov 2023 15:30 UTC

271 points

165 comments9 min readLW link

(thezvi.wordpress.com)

We don’t trade with ants

KatjaGrace10 Jan 2023 23:50 UTC

269 points

108 comments7 min readLW link

(worldspiritsockpuppet.com)

The Base Rate Times, news through prediction markets

vandemonian6 Jun 2023 17:42 UTC

268 points

40 comments4 min readLW link