How Death Feels

sisyphusDec 18, 2022, 11:47 PM
−7 points
9 comments1 min readLW link

Why Are Women Hot?

Jacob FalkovichDec 18, 2022, 11:20 PM
17 points
19 comments11 min readLW link

[Question] Can we, in prin­ci­ple, know the mea­sure of coun­ter­fac­tual quan­tum branches?

sisyphusDec 18, 2022, 10:07 PM
1 point
15 comments1 min readLW link

Bos­ton Sols­tice 2022 Retrospective

jefftkDec 18, 2022, 7:00 PM
19 points
3 comments5 min readLW link
(www.jefftk.com)

Take 11: “Align­ing lan­guage mod­els” should be weirder.

Charlie SteinerDec 18, 2022, 2:14 PM
34 points
0 comments2 min readLW link

Bad at Arith­metic, Promis­ing at Math

cohenmacaulayDec 18, 2022, 5:40 AM
100 points
19 comments20 min readLW link1 review

Over­con­fi­dence bubbles

kaputmiDec 18, 2022, 2:07 AM
3 points
0 comments2 min readLW link

Pos­i­tive val­ues seem more ro­bust and last­ing than prohibitions

TurnTroutDec 17, 2022, 9:43 PM
52 points
13 comments2 min readLW link

What we owe the microbiome

weverkaDec 17, 2022, 7:40 PM
2 points
0 comments1 min readLW link
(forum.effectivealtruism.org)

Why write more: im­prove your epistemics, self-care, & 28 other reasons

KatWoodsDec 17, 2022, 7:25 PM
24 points
1 comment6 min readLW link

Look­ing for an al­ign­ment tutor

JanBDec 17, 2022, 7:08 PM
15 points
2 comments1 min readLW link

[Question] How to Con­vince my Son that Drugs are Bad

concerned_dadDec 17, 2022, 6:47 PM
140 points
84 comments2 min readLW link

Or­di­nary hu­man life

David Hugh-JonesDec 17, 2022, 4:46 PM
24 points
3 comments14 min readLW link
(wyclif.substack.com)

Pre­dic­tive Pro­cess­ing, Hetero­sex­u­al­ity and Delu­sions of Grandeur

lsusrDec 17, 2022, 7:37 AM
37 points
13 comments5 min readLW link

[Link] Es­cape the Echo Cham­ber (2018)

CronoDASDec 17, 2022, 6:14 AM
13 points
0 comments2 min readLW link
(aeon.co)

“Starry Night” Sols­tice Cookies

maiaDec 17, 2022, 5:31 AM
26 points
7 comments1 min readLW link

There have been 3 planes (billion­aire donors) and 2 have crashed

trevorDec 17, 2022, 3:58 AM
16 points
10 comments2 min readLW link

[Question] What about non-de­gree seek­ing?

Lao MeinDec 17, 2022, 2:22 AM
5 points
5 comments1 min readLW link

Us­ing In­for­ma­tion The­ory to tackle AI Align­ment: A Prac­ti­cal Approach

Daniel SalamiDec 17, 2022, 1:37 AM
10 points
4 comments7 min readLW link

Paper: Con­sti­tu­tional AI: Harm­less­ness from AI Feed­back (An­thropic)

LawrenceCDec 16, 2022, 10:12 PM
68 points
11 comments1 min readLW link
(www.anthropic.com)

Vaguely in­ter­ested in Effec­tive Altru­ism? Please Take the Offi­cial 2022 EA Survey

Peter WildefordDec 16, 2022, 9:07 PM
22 points
4 comments1 min readLW link
(rethinkpriorities.qualtrics.com)

Ab­stract con­cepts and met­al­in­gual defi­ni­tion: Does ChatGPT un­der­stand jus­tice and char­ity?

Bill BenzonDec 16, 2022, 9:01 PM
2 points
0 comments13 min readLW link

Beyond the mo­ment of invention

jasoncrawfordDec 16, 2022, 8:18 PM
35 points
0 comments2 min readLW link
(rootsofprogress.org)

[Question] What’s the best time-effi­cient al­ter­na­tive to the Se­quences?

trevorDec 16, 2022, 8:17 PM
7 points
7 comments1 min readLW link

Can we effi­ciently ex­plain model be­hav­iors?

paulfchristianoDec 16, 2022, 7:40 PM
64 points
3 comments9 min readLW link
(ai-alignment.com)

Proper scor­ing rules don’t guaran­tee pre­dict­ing fixed points

Dec 16, 2022, 6:22 PM
79 points
8 comments21 min readLW link

A learned agent is not the same as a learn­ing agent

Ben AmitayDec 16, 2022, 5:27 PM
4 points
5 comments4 min readLW link

[Question] Col­lege Selec­tion Ad­vice for Tech­ni­cal Alignment

TempCollegeAskDec 16, 2022, 5:11 PM
11 points
8 comments1 min readLW link

How im­por­tant are ac­cu­rate AI timelines for the op­ti­mal spend­ing sched­ule on AI risk in­ter­ven­tions?

Tristan CookDec 16, 2022, 4:05 PM
27 points
2 commentsLW link

In­tro­duc­ing Shrubgrazer

jefftkDec 16, 2022, 2:50 PM
22 points
0 comments2 min readLW link
(www.jefftk.com)

Paper: Trans­form­ers learn in-con­text by gra­di­ent descent

LawrenceCDec 16, 2022, 11:10 AM
28 points
11 comments2 min readLW link
(arxiv.org)

Will Machines Ever Rule the World? MLAISU W50

Esben KranDec 16, 2022, 11:03 AM
12 points
7 comments4 min readLW link
(newsletter.apartresearch.com)

AI over­hangs de­pend on whether al­gorithms, com­pute and data are sub­sti­tutes or complements

NathanBarnardDec 16, 2022, 2:23 AM
2 points
0 comments3 min readLW link

AI Safety Move­ment Builders should help the com­mu­nity to op­ti­mise three fac­tors: con­trib­u­tors, con­tri­bu­tions and coordination

peterslatteryDec 15, 2022, 10:50 PM
4 points
0 comments6 min readLW link

Mask­ing to Avoid Miss­ing Things

jefftkDec 15, 2022, 9:00 PM
17 points
2 comments1 min readLW link
(www.jefftk.com)

Con­sider work­ing more hours and tak­ing more stimulants

Arjun PanicksseryDec 15, 2022, 8:38 PM
36 points
11 commentsLW link

We’ve stepped over the thresh­old into the Fourth Arena, but don’t rec­og­nize it

Bill BenzonDec 15, 2022, 8:22 PM
2 points
0 comments7 min readLW link

[Question] How is ARC plan­ning to use ELK?

jacquesthibsDec 15, 2022, 8:11 PM
24 points
5 comments1 min readLW link

How “Dis­cov­er­ing La­tent Knowl­edge in Lan­guage Models Without Su­per­vi­sion” Fits Into a Broader Align­ment Scheme

CollinDec 15, 2022, 6:22 PM
244 points
39 comments16 min readLW link1 review

High-level hopes for AI alignment

HoldenKarnofskyDec 15, 2022, 6:00 PM
58 points
3 comments19 min readLW link
(www.cold-takes.com)

Two Dog­mas of LessWrong

omnizoidDec 15, 2022, 5:56 PM
−7 points
155 comments69 min readLW link

Covid 12/​15/​22: China’s Wave Begins

ZviDec 15, 2022, 4:20 PM
32 points
7 comments10 min readLW link
(thezvi.wordpress.com)

The next decades might be wild

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

Ba­sic build­ing blocks of de­pen­dent type theory

Thomas KehrenbergDec 15, 2022, 2:54 PM
49 points
9 comments13 min readLW link

AI Ne­o­re­al­ism: a threat model & suc­cess crite­rion for ex­is­ten­tial safety

davidadDec 15, 2022, 1:42 PM
67 points
1 comment3 min readLW link

Who should write the defini­tive post on Ziz?

Nicholas / Heather KrossDec 15, 2022, 6:37 AM
4 points
45 comments3 min readLW link

[Question] Is Paul Chris­ti­ano still as op­ti­mistic about Ap­proval-Directed Agents as he was in 2018?

Chris_LeongDec 14, 2022, 11:28 PM
8 points
0 comments1 min readLW link

«Boundaries», Part 3b: Align­ment prob­lems in terms of bound­aries

Andrew_CritchDec 14, 2022, 10:34 PM
72 points
7 comments13 min readLW link

Align­ing al­ign­ment with performance

Marv KDec 14, 2022, 10:19 PM
2 points
0 comments2 min readLW link

Con­trary to List of Lethal­ity’s point 22, al­ign­ment’s door num­ber 2

False NameDec 14, 2022, 10:01 PM
−2 points
5 comments22 min readLW link