All2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025

AGI Ruin: A List of Lethalities

Eliezer Yudkowsky5 Jun 2022 22:05 UTC

940 points

708 comments30 min readLW link 3 reviews

Where I agree and disagree with Eliezer

paulfchristiano19 Jun 2022 19:15 UTC

900 points

223 comments18 min readLW link 2 reviews

Eight Short Studies On Excuses

Scott Alexander20 Apr 2010 23:01 UTC

860 points

253 comments10 min readLW link

Preface

Eliezer Yudkowsky11 Mar 2015 19:00 UTC

832 points

17 comments4 min readLW link

The Best Textbooks on Every Subject

lukeprog16 Jan 2011 8:30 UTC

774 points

417 comments7 min readLW link

What an actually pessimistic containment strategy looks like

lc5 Apr 2022 0:19 UTC

680 points

138 comments6 min readLW link 2 reviews

SolidGoldMagikarp (plus, prompt generation)

Jessica Rumbelow and mwatkins

5 Feb 2023 22:02 UTC

676 points

206 comments12 min readLW link 1 review

AI 2027: What Superintelligence Looks Like

Daniel Kokotajlo, Thomas Larsen, elifland, Scott Alexander, Jonas V and romeo

3 Apr 2025 16:23 UTC

644 points

218 comments41 min readLW link

(ai-2027.com)

Simulators

janus2 Sep 2022 12:45 UTC

634 points

168 comments41 min readLW link 8 reviews

(generative.ink)

The Waluigi Effect (mega-post)

Cleo Nardo3 Mar 2023 3:22 UTC

629 points

188 comments16 min readLW link

Schelling fences on slippery slopes

Scott Alexander16 Mar 2012 23:44 UTC

620 points

250 comments6 min readLW link

(The) Lightcone is nothing without its people: LW + Lighthaven’s big fundraiser

habryka30 Nov 2024 2:55 UTC

611 points

268 comments42 min readLW link

How to Make Superbabies

GeneSmith and kman

19 Feb 2025 20:39 UTC

602 points

349 comments31 min readLW link

Rationalism before the Sequences

Eric Raymond30 Mar 2021 14:04 UTC

596 points

83 comments11 min readLW link 2 reviews

Humans are not automatically strategic

AnnaSalamon8 Sep 2010 7:02 UTC

589 points

278 comments4 min readLW link

Making Vaccine

johnswentworth3 Feb 2021 20:24 UTC

587 points

249 comments6 min readLW link 3 reviews

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

habryka and kave

1 Apr 2024 7:33 UTC

571 points

181 comments11 min readLW link

Eliezer and I wrote a book: If Anyone Builds It, Everyone Dies

So8res14 May 2025 19:00 UTC

570 points

94 comments2 min readLW link

What 2026 looks like

Daniel Kokotajlo6 Aug 2021 16:14 UTC

567 points

161 comments16 min readLW link 1 review

Pain is not the unit of Effort

alkjash24 Nov 2020 20:00 UTC

566 points

92 comments5 min readLW link 2 reviews

(radimentary.wordpress.com)

Let’s think about slowing down AI

KatjaGrace22 Dec 2022 17:40 UTC

551 points

182 comments38 min readLW link 3 reviews

(aiimpacts.org)

Diseased thinking: dissolving questions about disease

Scott Alexander30 May 2010 21:16 UTC

540 points

356 comments9 min readLW link

OpenAI Email Archives (from Musk v. Altman and OpenAI blog)

habryka16 Nov 2024 6:38 UTC

531 points

80 comments51 min readLW link

The Talk: a brief explanation of sexual dimorphism

Malmesbury18 Sep 2023 16:23 UTC

526 points

75 comments16 min readLW link 3 reviews

Reason as memetic immune disorder

PhilGoetz19 Sep 2009 21:05 UTC

512 points

185 comments5 min readLW link

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 Redaction Machine

Ben20 Sep 2022 22:03 UTC

507 points

48 comments27 min readLW link 1 review

Making Beliefs Pay Rent (in Anticipated Experiences)

Eliezer Yudkowsky28 Jul 2007 22:59 UTC

503 points

268 comments4 min readLW link

Luck based medicine: my resentful story of becoming a medical miracle

Elizabeth16 Oct 2022 17:40 UTC

489 points

121 comments12 min readLW link 3 reviews

(acesounderglass.com)

Alignment Faking in Large Language Models

ryan_greenblatt, evhub, Carson Denison, Benjamin Wright, Fabien Roger, Monte M, Sam Marks, Johannes Treutlein, Sam Bowman and Buck

18 Dec 2024 17:19 UTC

483 points

75 comments10 min readLW link

Losing the root for the tree

Adam Zerner20 Sep 2022 4:53 UTC

482 points

31 comments9 min readLW link 1 review

Being the (Pareto) Best in the World

johnswentworth24 Jun 2019 18:36 UTC

474 points

60 comments3 min readLW link 3 reviews

The ants and the grasshopper

Richard_Ngo4 Jun 2023 22:00 UTC

465 points

44 comments5 min readLW link 4 reviews

(www.narrativeark.xyz)

Welcome to LessWrong!

Ruby, Raemon, RobertM and habryka

14 Jun 2019 19:42 UTC

465 points

65 comments2 min readLW link

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

So8res2 Feb 2023 0:27 UTC

463 points

64 comments4 min readLW link 3 reviews

I would have shit in that alley, too

Declan Molony18 Jun 2024 4:41 UTC

462 points

134 comments4 min readLW link

Significantly Enhancing Adult Intelligence With Gene Editing May Be Possible

GeneSmith and kman

12 Dec 2023 18:14 UTC

459 points

206 comments33 min readLW link 2 reviews

How To Write Quickly While Maintaining Epistemic Rigor

johnswentworth28 Aug 2021 17:52 UTC

458 points

38 comments4 min readLW link 3 reviews

100 Tips for a Better Life

Ideopunk22 Dec 2020 14:30 UTC

456 points

130 comments9 min readLW link 1 review

Counter-theses on Sleep

Natália21 Mar 2022 23:21 UTC

447 points

135 comments15 min readLW link 1 review

Orienting Toward Wizard Power

johnswentworth8 May 2025 5:23 UTC

443 points

99 comments5 min readLW link

It’s Probably Not Lithium

Natália28 Jun 2022 21:24 UTC

442 points

187 comments28 min readLW link 1 review

Generalizing From One Example

Scott Alexander28 Apr 2009 22:00 UTC

438 points

423 comments6 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

437 points

98 comments50 min readLW link 1 review

What failure looks like

paulfchristiano17 Mar 2019 20:18 UTC

434 points

55 comments8 min readLW link 2 reviews

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

jenn1 Jun 2023 20:48 UTC

430 points

35 comments8 min readLW link 1 review

(jenn.site)

The Best Tacit Knowledge Videos on Every Subject

Parker Conley31 Mar 2024 17:14 UTC

427 points

157 comments16 min readLW link

The noncentral fallacy—the worst argument in the world?

Scott Alexander27 Aug 2012 3:36 UTC

426 points

1,769 comments7 min readLW link

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)

Bets, Bonds, and Kindergarteners

jefftk3 Jan 2021 21:20 UTC

425 points

35 comments2 min readLW link 1 review

(www.jefftk.com)