[UPDATE: dead­line ex­tended to July 24!] New wind in ra­tio­nal­ity’s sails: Ap­pli­ca­tions for Epistea Res­i­dency 2023 are now open

Jul 11, 2023, 11:02 AM
80 points
7 comments3 min readLW link

Drawn Out: a story

Richard_NgoJul 11, 2023, 12:08 AM
80 points
2 comments8 min readLW link

You don’t get to have cool flaws

Neil Jul 28, 2023, 5:37 AM
78 points
25 comments2 min readLW link3 reviews

A re­for­mu­la­tion of Finite Fac­tored Sets

Matthias G. MayerJul 24, 2023, 1:02 PM
76 points
1 comment8 min readLW link

Why You Should Never Up­date Your Beliefs

Arjun PanicksseryJul 29, 2023, 12:27 AM
76 points
18 comments4 min readLW link1 review
(arjunpanickssery.substack.com)

Elon Musk an­nounces xAI

Jan_KulveitJul 13, 2023, 9:01 AM
75 points
35 comments1 min readLW link
(www.ft.com)

An­nounc­ing Man­i­fund Regrants

Austin ChenJul 5, 2023, 7:42 PM
74 points
8 commentsLW link

SSA re­jects an­thropic shadow, too

jessicataJul 27, 2023, 5:25 PM
74 points
38 comments11 min readLW link
(unstableontology.com)

Thoughts on “Pro­cess-Based Su­per­vi­sion”

Steven ByrnesJul 17, 2023, 2:08 PM
74 points
4 comments23 min readLW link

Ex­is­ten­tial Risk Per­sua­sion Tournament

PeterMcCluskeyJul 17, 2023, 6:04 PM
73 points
1 comment8 min readLW link
(bayesianinvestor.com)

A brief his­tory of computers

Adam ZernerJul 19, 2023, 2:59 AM
73 points
18 comments33 min readLW link

Six (and a half) in­tu­itions for SVD

CallumMcDougallJul 4, 2023, 7:23 PM
71 points
1 comment1 min readLW link

[Question] I’m con­sis­tently over­whelmed by ba­sic obli­ga­tions. Are there any paradigm shifts or other ra­tio­nal­ity-based tips that would be helpful?

Benjamin HendricksJul 21, 2023, 9:10 PM
71 points
42 comments2 min readLW link

An­nounce­ment: AI Nar­ra­tions Available for All New LessWrong Posts

Jul 20, 2023, 10:17 PM
71 points
28 comments1 min readLW link

Gra­di­ent de­scent might see the di­rec­tion of the op­ti­mum from far away

Mikhail SaminJul 28, 2023, 4:19 PM
70 points
13 comments4 min readLW link

An Overview of the AI Safety Fund­ing Situation

Stephen McAleeseJul 12, 2023, 2:54 PM
69 points
10 commentsLW link

Really Strong Fea­tures Found in Resi­d­ual Stream

Logan RiggsJul 8, 2023, 7:40 PM
69 points
6 comments2 min readLW link

Pre­dic­tive his­tory classes

dkl9Jul 17, 2023, 8:48 PM
68 points
17 comments2 min readLW link
(dkl9.net)

Mech In­terp Puz­zle 1: Sus­pi­ciously Similar Embed­dings in GPT-Neo

Neel NandaJul 16, 2023, 10:02 PM
67 points
15 comments1 min readLW link

Open-minded updatelessness

Jul 10, 2023, 11:08 AM
66 points
21 comments12 min readLW link

Alpha

Erich_GrunewaldJul 1, 2023, 4:05 PM
65 points
2 comments14 min readLW link
(www.erichgrunewald.com)

The virtue of determination

Richard_NgoJul 10, 2023, 5:11 AM
65 points
5 comments4 min readLW link

News : Bi­den-⁠Har­ris Ad­minis­tra­tion Se­cures Vol­un­tary Com­mit­ments from Lead­ing Ar­tifi­cial In­tel­li­gence Com­pa­nies to Man­age the Risks Posed by AI

Jonathan ClaybroughJul 21, 2023, 6:00 PM
65 points
10 comments2 min readLW link
(www.whitehouse.gov)

Meta-ra­tio­nal­ity and frames

Richard_NgoJul 3, 2023, 12:33 AM
64 points
2 comments5 min readLW link

Micro Habits that Im­prove One’s Day

silentbobJul 1, 2023, 10:53 AM
64 points
9 comments5 min readLW link

Why no Ro­man In­dus­trial Revolu­tion?

jasoncrawfordJul 26, 2023, 7:34 PM
62 points
30 comments3 min readLW link
(rootsofprogress.org)

Pul­ling the Rope Side­ways: Em­piri­cal Test Results

Daniel KokotajloJul 27, 2023, 10:18 PM
61 points
18 comments1 min readLW link

[Question] The liter­a­ture on alu­minum ad­ju­vants is very sus­pi­cious. Small IQ tax is plau­si­ble—can any ex­perts help me es­ti­mate it?

mikesJul 4, 2023, 9:33 AM
61 points
39 comments3 min readLW link

(ten­ta­tively) Found 600+ Monose­man­tic Fea­tures in a Small LM Us­ing Sparse Autoencoders

Logan RiggsJul 5, 2023, 4:49 PM
60 points
1 comment7 min readLW link

Agency begets agency

Richard_NgoJul 6, 2023, 1:08 PM
60 points
1 comment4 min readLW link

Fo­rum Karma: view stats and find highly-rated com­ments for any LW user

Max HJul 1, 2023, 3:36 PM
60 points
16 comments2 min readLW link
(forumkarma.com)

[Question] Which ra­tio­nal­ity posts are beg­ging for fur­ther prac­ti­cal de­vel­op­ment?

LoganStrohlJul 23, 2023, 10:22 PM
60 points
17 comments1 min readLW link

AI #20: Code In­ter­preter and Claude 2.0 for Everyone

ZviJul 13, 2023, 2:00 PM
60 points
9 comments56 min readLW link
(thezvi.wordpress.com)

AI #19: Hofs­tadter, Sutskever, Leike

ZviJul 6, 2023, 12:50 PM
60 points
16 comments40 min readLW link
(thezvi.wordpress.com)

Au­toIn­ter­pre­ta­tion Finds Sparse Cod­ing Beats Alternatives

HoagyJul 17, 2023, 1:41 AM
57 points
1 comment7 min readLW link

An up­com­ing US Supreme Court case may im­pede AI gov­er­nance efforts

NickGabsJul 16, 2023, 11:51 PM
57 points
17 comments2 min readLW link

How to make real-money pre­dic­tion mar­kets on ar­bi­trary top­ics (Out­dated)

yutakaJul 30, 2023, 2:11 AM
57 points
13 comments3 min readLW link

Ra­tional Unilat­er­al­ists Aren’t So Cursed

SCPJul 4, 2023, 12:19 PM
56 points
6 comments6 min readLW link1 review

A re­view of Prin­cipia Qualia

jessicataJul 12, 2023, 6:38 PM
56 points
8 comments10 min readLW link
(unstablerontology.substack.com)

Train­ing Pro­cess Trans­parency through Gra­di­ent In­ter­pretabil­ity: Early ex­per­i­ments on toy lan­guage models

Jul 21, 2023, 2:52 PM
56 points
1 comment1 min readLW link

Par­tial Tran­script of Re­cent Se­nate Hear­ing Dis­cussing AI X-Risk

Daniel_EthJul 27, 2023, 9:16 AM
55 points
0 commentsLW link
(medium.com)

In­ter­nal in­de­pen­dent re­view for lan­guage model agent alignment

Seth HerdJul 7, 2023, 6:54 AM
55 points
30 comments11 min readLW link

AXRP Epi­sode 24 - Su­per­al­ign­ment with Jan Leike

DanielFilanJul 27, 2023, 4:00 AM
55 points
3 comments69 min readLW link

Align­ment Me­gapro­jects: You’re Not Even Try­ing to Have Ideas

Nicholas / Heather KrossJul 12, 2023, 11:39 PM
55 points
32 comments2 min readLW link

Aging and the gero­science hypothesis

DirectedEvolutionJul 12, 2023, 7:16 AM
54 points
14 comments5 min readLW link

Boundary Place­ment Rebellion

tailcalledJul 20, 2023, 5:40 PM
54 points
21 comments12 min readLW link

Thoughts on Loss Land­scapes and why Deep Learn­ing works

berenJul 25, 2023, 4:41 PM
53 points
4 comments18 min readLW link

Op­ti­mized for Some­thing other than Win­ning or: How Cricket Re­sists Moloch and Good­hart’s Law

A.H.Jul 5, 2023, 12:33 PM
53 points
26 comments4 min readLW link

Ac­ti­va­tion adding ex­per­i­ments with llama-7b

Nina PanicksseryJul 16, 2023, 4:17 AM
51 points
1 comment3 min readLW link

Dom­i­nant As­surance Con­tract Ex­per­i­ment #2: Berkeley House Dinners

Arjun PanicksseryJul 5, 2023, 12:13 AM
51 points
8 comments1 min readLW link
(arjunpanickssery.substack.com)