All200520062007200820092010201120122013201420152016201720182019202020212022202320242025

AGI Ruin: A List of Lethalities

Eliezer Yudkowsky5 Jun 2022 22:05 UTC
921 points
704 comments30 min readLW link3 reviews

Where I agree and dis­agree with Eliezer

paulfchristiano19 Jun 2022 19:15 UTC
890 points
223 comments18 min readLW link2 reviews

Eight Short Stud­ies On Excuses

Scott Alexander20 Apr 2010 23:01 UTC
839 points
253 comments10 min readLW link

Preface

Eliezer Yudkowsky11 Mar 2015 19:00 UTC
791 points
15 comments4 min readLW link

The Best Text­books on Every Subject

lukeprog16 Jan 2011 8:30 UTC
751 points
414 comments7 min readLW link

SolidGoldMag­ikarp (plus, prompt gen­er­a­tion)

Jessica Rumbelow and mwatkins
5 Feb 2023 22:02 UTC
677 points
206 comments12 min readLW link1 review

What an ac­tu­ally pes­simistic con­tain­ment strat­egy looks like

lc5 Apr 2022 0:19 UTC
676 points
138 comments6 min readLW link2 reviews

The Waluigi Effect (mega-post)

Cleo Nardo3 Mar 2023 3:22 UTC
632 points
188 comments16 min readLW link

Simulators

janus2 Sep 2022 12:45 UTC
614 points
168 comments41 min readLW link8 reviews
(generative.ink)

Schel­ling fences on slip­pery slopes

Scott Alexander16 Mar 2012 23:44 UTC
599 points
250 comments6 min readLW link

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

habryka30 Nov 2024 2:55 UTC
596 points
243 comments42 min readLW link

Ra­tion­al­ism be­fore the Sequences

Eric Raymond30 Mar 2021 14:04 UTC
594 points
83 comments11 min readLW link2 reviews

Mak­ing Vaccine

johnswentworth3 Feb 2021 20:24 UTC
579 points
249 comments6 min readLW link3 reviews

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

habryka and kave
1 Apr 2024 7:33 UTC
566 points
179 comments11 min readLW link

Hu­mans are not au­to­mat­i­cally strategic

AnnaSalamon8 Sep 2010 7:02 UTC
561 points
278 comments4 min readLW link

Let’s think about slow­ing down AI

KatjaGrace22 Dec 2022 17:40 UTC
551 points
182 comments38 min readLW link3 reviews
(aiimpacts.org)

Pain is not the unit of Effort

alkjash24 Nov 2020 20:00 UTC
550 points
90 comments5 min readLW link2 reviews
(radimentary.wordpress.com)

Diseased think­ing: dis­solv­ing ques­tions about disease

Scott Alexander30 May 2010 21:16 UTC
530 points
356 comments9 min readLW link

What 2026 looks like

Daniel Kokotajlo6 Aug 2021 16:14 UTC
525 points
156 comments16 min readLW link1 review

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

habryka16 Nov 2024 6:38 UTC
523 points
80 comments51 min readLW link

The Talk: a brief ex­pla­na­tion of sex­ual dimorphism

Malmesbury18 Sep 2023 16:23 UTC
508 points
75 comments16 min readLW link3 reviews

The Redac­tion Machine

Ben20 Sep 2022 22:03 UTC
502 points
48 comments27 min readLW link1 review

Rea­son as memetic im­mune disorder

PhilGoetz19 Sep 2009 21:05 UTC
500 points
185 comments5 min readLW link

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

Elizabeth16 Oct 2022 17:40 UTC
485 points
121 comments12 min readLW link3 reviews
(acesounderglass.com)

How much do you be­lieve your re­sults?

Eric Neyman6 May 2023 20:31 UTC
483 points
17 comments15 min readLW link3 reviews
(ericneyman.wordpress.com)

Mak­ing Beliefs Pay Rent (in An­ti­ci­pated Ex­pe­riences)

Eliezer Yudkowsky28 Jul 2007 22:59 UTC
478 points
267 comments4 min readLW link

Los­ing the root for the tree

Adam Zerner20 Sep 2022 4:53 UTC
475 points
31 comments9 min readLW link1 review

Be­ing the (Pareto) Best in the World

johnswentworth24 Jun 2019 18:36 UTC
462 points
60 comments3 min readLW link3 reviews

How To Write Quickly While Main­tain­ing Epistemic Rigor

johnswentworth28 Aug 2021 17:52 UTC
453 points
38 comments4 min readLW link3 reviews

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
451 points
53 comments10 min readLW link

100 Tips for a Bet­ter Life

Ideopunk22 Dec 2020 14:30 UTC
450 points
130 comments9 min readLW link1 review

Counter-the­ses on Sleep

Natália21 Mar 2022 23:21 UTC
446 points
135 comments15 min readLW link1 review

Sig­nifi­cantly En­hanc­ing Adult In­tel­li­gence With Gene Edit­ing May Be Possible

GeneSmith and kman
12 Dec 2023 18:14 UTC
443 points
198 comments33 min readLW link1 review

It’s Prob­a­bly Not Lithium

Natália28 Jun 2022 21:24 UTC
442 points
187 comments28 min readLW link1 review

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

So8res2 Feb 2023 0:27 UTC
440 points
63 comments4 min readLW link3 reviews

I would have shit in that alley, too

Declan Molony18 Jun 2024 4:41 UTC
440 points
135 comments4 min readLW link

The ants and the grasshopper

Richard_Ngo4 Jun 2023 22:00 UTC
440 points
38 comments5 min readLW link2 reviews
(www.narrativeark.xyz)

Wel­come to LessWrong!

Ruby, Raemon, RobertM and habryka
14 Jun 2019 19:42 UTC
437 points
63 comments2 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 link1 review

Gen­er­al­iz­ing From One Example

Scott Alexander28 Apr 2009 22:00 UTC
437 points
423 comments6 min readLW link

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)

Bets, Bonds, and Kindergarteners

jefftk3 Jan 2021 21:20 UTC
421 points
35 comments2 min readLW link1 review
(www.jefftk.com)

The non­cen­tral fal­lacy—the worst ar­gu­ment in the world?

Scott Alexander27 Aug 2012 3:36 UTC
421 points
1,768 comments7 min readLW link

chin­chilla’s wild implications

nostalgebraist31 Jul 2022 1:18 UTC
420 points
128 comments10 min readLW link1 review

What failure looks like

paulfchristiano17 Mar 2019 20:18 UTC
419 points
54 comments8 min readLW link2 reviews

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

jenn1 Jun 2023 20:48 UTC
416 points
35 comments8 min readLW link1 review
(jenn.site)

(My un­der­stand­ing of) What Every­one in Tech­ni­cal Align­ment is Do­ing and Why

Thomas Larsen and elifland
29 Aug 2022 1:23 UTC
413 points
90 comments37 min readLW link1 review

Trans­form­ers Rep­re­sent Belief State Geom­e­try in their Resi­d­ual Stream

Adam Shai16 Apr 2024 21:16 UTC
412 points
100 comments12 min readLW link

Failures in Kindness

silentbob26 Mar 2024 21:30 UTC
411 points
60 comments9 min readLW link

GPTs are Pre­dic­tors, not Imitators

Eliezer Yudkowsky8 Apr 2023 19:59 UTC
409 points
99 comments3 min readLW link3 reviews