AGI Ruin: A List of Lethalities

Eliezer YudkowskyJun 5, 2022, 10:05 PM
945 points
710 comments30 min readLW link3 reviews

Where I agree and dis­agree with Eliezer

paulfchristianoJun 19, 2022, 7:15 PM
901 points
224 comments18 min readLW link2 reviews

Eight Short Stud­ies On Excuses

Scott AlexanderApr 20, 2010, 11:01 PM
863 points
253 comments10 min readLW link

Preface

Eliezer YudkowskyMar 11, 2015, 7:00 PM
839 points
17 comments4 min readLW link

The Best Text­books on Every Subject

lukeprogJan 16, 2011, 8:30 AM
785 points
417 comments7 min readLW link

What an ac­tu­ally pes­simistic con­tain­ment strat­egy looks like

lcApr 5, 2022, 12:19 AM
680 points
138 comments6 min readLW link2 reviews

SolidGoldMag­ikarp (plus, prompt gen­er­a­tion)

Feb 5, 2023, 10:02 PM
676 points
206 comments12 min readLW link1 review

AI 2027: What Su­per­in­tel­li­gence Looks Like

Apr 3, 2025, 4:23 PM
657 points
220 comments41 min readLW link
(ai-2027.com)

Simulators

janusSep 2, 2022, 12:45 PM
636 points
168 comments41 min readLW link8 reviews
(generative.ink)

The Waluigi Effect (mega-post)

Cleo NardoMar 3, 2023, 3:22 AM
630 points
188 comments16 min readLW link

Schel­ling fences on slip­pery slopes

Scott AlexanderMar 16, 2012, 11:44 PM
624 points
250 comments6 min readLW link

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

So8resMay 14, 2025, 7:00 PM
621 points
109 comments2 min readLW link

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

habrykaNov 30, 2024, 2:55 AM
610 points
270 comments42 min readLW link

How to Make Superbabies

Feb 19, 2025, 8:39 PM
609 points
351 comments31 min readLW link

Ra­tion­al­ism be­fore the Sequences

Eric RaymondMar 30, 2021, 2:04 PM
597 points
83 comments11 min readLW link2 reviews

Hu­mans are not au­to­mat­i­cally strategic

AnnaSalamonSep 8, 2010, 7:02 AM
593 points
278 comments4 min readLW link

Mak­ing Vaccine

johnswentworthFeb 3, 2021, 8:24 PM
589 points
249 comments6 min readLW link3 reviews

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

Apr 1, 2024, 7:33 AM
571 points
181 comments11 min readLW link

What 2026 looks like

Daniel KokotajloAug 6, 2021, 4:14 PM
571 points
162 comments16 min readLW link1 review

Pain is not the unit of Effort

alkjashNov 24, 2020, 8:00 PM
568 points
92 comments5 min readLW link2 reviews
(radimentary.wordpress.com)

Let’s think about slow­ing down AI

KatjaGraceDec 22, 2022, 5:40 PM
551 points
182 comments38 min readLW link3 reviews
(aiimpacts.org)

Diseased think­ing: dis­solv­ing ques­tions about disease

Scott AlexanderMay 30, 2010, 9:16 PM
541 points
356 comments9 min readLW link

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

habrykaNov 16, 2024, 6:38 AM
531 points
80 comments51 min readLW link

The Talk: a brief ex­pla­na­tion of sex­ual dimorphism

MalmesburySep 18, 2023, 4:23 PM
529 points
77 comments16 min readLW link3 reviews

Ori­ent­ing Toward Wizard Power

johnswentworthMay 8, 2025, 5:23 AM
524 points
136 comments5 min readLW link

Rea­son as memetic im­mune disorder

PhilGoetzSep 19, 2009, 9:05 PM
514 points
185 comments5 min readLW link

Mak­ing Beliefs Pay Rent (in An­ti­ci­pated Ex­pe­riences)

Eliezer YudkowskyJul 28, 2007, 10:59 PM
510 points
268 comments4 min readLW link

How much do you be­lieve your re­sults?

Eric NeymanMay 6, 2023, 8:31 PM
508 points
18 comments15 min readLW link4 reviews
(ericneyman.wordpress.com)

The Redac­tion Machine

BenSep 20, 2022, 10:03 PM
507 points
48 comments27 min readLW link1 review

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

ElizabethOct 16, 2022, 5:40 PM
490 points
121 comments12 min readLW link3 reviews
(acesounderglass.com)

Align­ment Fak­ing in Large Lan­guage Models

Dec 18, 2024, 5:19 PM
485 points
75 comments10 min readLW link

Los­ing the root for the tree

Adam ZernerSep 20, 2022, 4:53 AM
482 points
31 comments9 min readLW link1 review

Be­ing the (Pareto) Best in the World

johnswentworthJun 24, 2019, 6:36 PM
475 points
60 comments3 min readLW link3 reviews

Wel­come to LessWrong!

Jun 14, 2019, 7:42 PM
467 points
74 comments2 min readLW link

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

So8resFeb 2, 2023, 12:27 AM
466 points
64 comments4 min readLW link3 reviews

The ants and the grasshopper

Richard_NgoJun 4, 2023, 10:00 PM
465 points
44 comments5 min readLW link4 reviews
(www.narrativeark.xyz)

I would have shit in that alley, too

Declan MolonyJun 18, 2024, 4:41 AM
462 points
134 comments4 min readLW link

How To Write Quickly While Main­tain­ing Epistemic Rigor

johnswentworthAug 28, 2021, 5:52 PM
459 points
38 comments4 min readLW link3 reviews

Sig­nifi­cantly En­hanc­ing Adult In­tel­li­gence With Gene Edit­ing May Be Possible

Dec 12, 2023, 6:14 PM
459 points
206 comments33 min readLW link2 reviews

100 Tips for a Bet­ter Life

IdeopunkDec 22, 2020, 2:30 PM
458 points
130 comments9 min readLW link1 review

What We Learned from Briefing 70+ Law­mak­ers on the Threat from AI

leticiagarciaMay 27, 2025, 6:23 PM
450 points
14 comments16 min readLW link
(substack.com)

Counter-the­ses on Sleep

NatáliaMar 21, 2022, 11:21 PM
447 points
135 comments15 min readLW link1 review

It’s Prob­a­bly Not Lithium

NatáliaJun 28, 2022, 9:24 PM
442 points
187 comments28 min readLW link1 review

Gen­er­al­iz­ing From One Example

Scott AlexanderApr 28, 2009, 10:00 PM
440 points
423 comments6 min readLW link

Steer­ing GPT-2-XL by adding an ac­ti­va­tion vector

May 13, 2023, 6:42 PM
437 points
98 comments50 min readLW link1 review

What failure looks like

paulfchristianoMar 17, 2019, 8:18 PM
435 points
55 comments8 min readLW link2 reviews

The Best Tacit Knowl­edge Videos on Every Subject

Parker ConleyMar 31, 2024, 5:14 PM
434 points
159 comments16 min readLW link

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

jennJun 1, 2023, 8:48 PM
432 points
35 comments8 min readLW link1 review
(jenn.site)

The non­cen­tral fal­lacy—the worst ar­gu­ment in the world?

Scott AlexanderAug 27, 2012, 3:36 AM
427 points
1,769 comments7 min readLW link

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

gwernJul 3, 2023, 12:48 AM
427 points
54 comments7 min readLW link
(www.youtube.com)