All200520062007200820092010201120122013201420152016201720182019202020212022202320242025
AllJanFebMarAprMayJunJulAugSepOctNovDec

dalle2 comments

nostalgebraistApr 26, 2022, 5:30 AM
183 points
14 comments13 min readLW link
(nostalgebraist.tumblr.com)

Look For Prin­ci­ples Which Will Carry Over To The Next Paradigm

johnswentworthJan 14, 2022, 8:22 PM
182 points
7 comments5 min readLW link1 review

Lan­guage mod­els seem to be much bet­ter than hu­mans at next-to­ken prediction

Buck, Fabien Roger and LawrenceC
Aug 11, 2022, 5:45 PM
182 points
60 comments13 min readLW link1 review

Con­jec­ture: a ret­ro­spec­tive af­ter 8 months of work

Connor Leahy, Sid Black, Gabriel Alfour and Chris Scammell
Nov 23, 2022, 5:10 PM
180 points
9 comments8 min readLW link

The pro­to­typ­i­cal catas­trophic AI ac­tion is get­ting root ac­cess to its datacenter

BuckJun 2, 2022, 11:46 PM
180 points
13 comments2 min readLW link1 review

Post­mortem on DIY Re­com­bi­nant Covid Vaccine

caffemacchiavelliJan 22, 2022, 2:12 PM
179 points
27 comments5 min readLW link1 review

IMO challenge bet with Eliezer

paulfchristianoFeb 26, 2022, 4:50 AM
179 points
26 comments3 min readLW link

Some con­cep­tual al­ign­ment re­search projects

Richard_NgoAug 25, 2022, 10:51 PM
177 points
15 comments3 min readLW link

AGI ruin sce­nar­ios are likely (and dis­junc­tive)

So8resJul 27, 2022, 3:21 AM
177 points
38 comments6 min readLW link

7 traps that (we think) new al­ign­ment re­searchers of­ten fall into

Orpheus16 and Thomas Larsen
Sep 27, 2022, 11:13 PM
176 points
10 comments4 min readLW link

Geo­met­ric Ra­tion­al­ity is Not VNM Rational

Scott GarrabrantNov 27, 2022, 7:36 PM
176 points
27 comments3 min readLW link

What AI Safety Ma­te­ri­als Do ML Re­searchers Find Com­pel­ling?

Vael Gates and Collin
Dec 28, 2022, 2:03 AM
175 points
34 comments2 min readLW link

The next decades might be wild

Marius HobbhahnDec 15, 2022, 4:10 PM
175 points
42 comments41 min readLW link1 review

Rus­sia has In­vaded Ukraine

lsusrFeb 24, 2022, 7:52 AM
174 points
268 comments3 min readLW link

Finite Fac­tored Sets in Pictures

Magdalena WacheDec 11, 2022, 6:49 PM
174 points
35 comments12 min readLW link

The in­or­di­nately slow spread of good AGI con­ver­sa­tions in ML

Rob BensingerJun 21, 2022, 4:09 PM
173 points
62 comments8 min readLW link

What’s Up With Con­fus­ingly Per­va­sive Goal Direct­ed­ness?

RaemonJan 20, 2022, 7:22 PM
172 points
89 comments4 min readLW link

An­nounc­ing the In­verse Scal­ing Prize ($250k Prize Pool)

Ethan Perez, Ian McKenzie and Sam Bowman
Jun 27, 2022, 3:58 PM
171 points
14 comments7 min readLW link

De­ci­sion the­ory does not im­ply that we get to have nice things

So8resOct 18, 2022, 3:04 AM
171 points
73 comments26 min readLW link2 reviews

Tran­scripts of in­ter­views with AI researchers

Vael GatesMay 9, 2022, 5:57 AM
170 points
9 comments2 min readLW link

Do bam­boos set them­selves on fire?

MalmesburySep 19, 2022, 3:34 PM
170 points
14 comments6 min readLW link1 review

Us­ing GPT-Eliezer against ChatGPT Jailbreaking

Stuart_Armstrong and rgorman
Dec 6, 2022, 7:54 PM
170 points
85 comments9 min readLW link

Six (and a half) in­tu­itions for KL divergence

CallumMcDougallOct 12, 2022, 9:07 PM
170 points
27 comments10 min readLW link1 review
(www.perfectlynormal.co.uk)

AI Could Defeat All Of Us Combined

HoldenKarnofskyJun 9, 2022, 3:50 PM
170 points
42 comments17 min readLW link
(www.cold-takes.com)

Search­ing for outliers

benkuhnMar 21, 2022, 2:40 AM
169 points
16 comments18 min readLW link1 review
(www.benkuhn.net)

Planes are still decades away from dis­plac­ing most bird jobs

guzeyNov 25, 2022, 4:49 PM
168 points
13 comments3 min readLW link

Im­pos­si­bil­ity re­sults for un­bounded utilities

paulfchristianoFeb 2, 2022, 3:52 AM
167 points
109 comments8 min readLW link1 review

Shard The­ory: An Overview

David UdellAug 11, 2022, 5:44 AM
166 points
34 comments10 min readLW link

Things that can kill you quickly: What ev­ery­one should know about first aid

jasoncrawfordDec 27, 2022, 4:23 PM
166 points
21 comments2 min readLW link1 review
(jasoncrawford.org)

Play­ing with DALL·E 2

Dave OrrApr 7, 2022, 6:49 PM
166 points
118 comments6 min readLW link

[Beta Fea­ture] Google-Docs-like edit­ing for LessWrong posts

Ruby and jimrandomh
Feb 23, 2022, 1:52 AM
165 points
26 comments3 min readLW link

The So­cial Re­ces­sion: By the Numbers

antonomonOct 29, 2022, 6:45 PM
165 points
29 comments8 min readLW link
(novum.substack.com)

Every­thing I Need To Know About Take­off Speeds I Learned From Air Con­di­tioner Rat­ings On Amazon

johnswentworthApr 15, 2022, 7:05 PM
165 points
128 comments5 min readLW link

On A List of Lethalities

ZviJun 13, 2022, 12:30 PM
165 points
50 comments54 min readLW link1 review
(thezvi.wordpress.com)

Deep­mind’s Gato: Gen­er­al­ist Agent

Daniel KokotajloMay 12, 2022, 4:01 PM
165 points
62 comments1 min readLW link

Most Peo­ple Start With The Same Few Bad Ideas

johnswentworth9 Sep 2022 0:29 UTC
165 points
30 comments3 min readLW link

Why I think there’s a one-in-six chance of an im­mi­nent global nu­clear war

Max Tegmark8 Oct 2022 6:26 UTC
164 points
169 comments4 min readLW link

A trans­parency and in­ter­pretabil­ity tech tree

evhub16 Jun 2022 23:44 UTC
163 points
11 comments18 min readLW link1 review

The Onion Test for Per­sonal and In­sti­tu­tional Honesty

chanamessinger and Andrew_Critch
27 Sep 2022 15:26 UTC
163 points
31 comments3 min readLW link3 reviews

Log­i­cal in­duc­tion for soft­ware engineers

Alex Flint3 Dec 2022 19:55 UTC
163 points
8 comments27 min readLW link1 review

Be less scared of overconfidence

benkuhn30 Nov 2022 15:20 UTC
163 points
22 comments9 min readLW link
(www.benkuhn.net)

A Bird’s Eye View of the ML Field [Prag­matic AI Safety #2]

Dan H and TW123
9 May 2022 17:18 UTC
163 points
8 comments35 min readLW link

ITT-pass­ing and ci­vil­ity are good; “char­ity” is bad; steel­man­ning is niche

Rob Bensinger5 Jul 2022 0:15 UTC
163 points
36 comments6 min readLW link1 review

Threat-Re­sis­tant Bar­gain­ing Me­ga­post: In­tro­duc­ing the ROSE Value

Diffractor28 Sep 2022 1:20 UTC
162 points
19 comments53 min readLW link2 reviews

Deep Learn­ing Sys­tems Are Not Less In­ter­pretable Than Logic/​Prob­a­bil­ity/​Etc

johnswentworth4 Jun 2022 5:41 UTC
160 points
55 comments2 min readLW link1 review

[In­tro to brain-like-AGI safety] 1. What’s the prob­lem & Why work on it now?

Steven Byrnes26 Jan 2022 15:23 UTC
159 points
19 comments26 min readLW link

The Geo­met­ric Expectation

Scott Garrabrant23 Nov 2022 18:05 UTC
159 points
22 comments4 min readLW link

Godzilla Strategies

johnswentworth11 Jun 2022 15:44 UTC
159 points
72 comments3 min readLW link

Re­peal the For­eign Dredge Act of 1906

Zvi5 May 2022 15:20 UTC
159 points
16 comments19 min readLW link
(thezvi.wordpress.com)

Why all the fuss about re­cur­sive self-im­prove­ment?

So8res12 Jun 2022 20:53 UTC
158 points
62 comments7 min readLW link1 review