China’s po­si­tion on au­tonomous weapons

bhauthAug 23, 2023, 10:20 PM
17 points
2 comments1 min readLW link
(academic.oup.com)

Diet Ex­per­i­ment Pr­ereg­is­tra­tion: Long-term wa­ter fast­ing + seed oil re­moval

lcAug 23, 2023, 10:08 PM
56 points
18 comments1 min readLW link

The Low-Hang­ing Fruit Prior and sloped valleys in the loss landscape

Aug 23, 2023, 9:12 PM
82 points
1 comment13 min readLW link

Govern­ing, Fast and Slow

CarsonAug 23, 2023, 8:01 PM
3 points
0 comments3 min readLW link

A prob­lem with the most re­cently pub­lished ver­sion of CEV

ThomasCederborgAug 23, 2023, 6:05 PM
10 points
8 comments8 min readLW link1 review

[Question] Which paths to pow­er­ful AI should be boosted?

Zach Stein-PerlmanAug 23, 2023, 4:00 PM
5 points
1 comment1 min readLW link

A The­ory of Laughter

Steven ByrnesAug 23, 2023, 3:05 PM
102 points
14 comments28 min readLW link

Why Is No One Try­ing To Align Profit In­cen­tives With Align­ment Re­search?

PrometheusAug 23, 2023, 1:16 PM
51 points
11 comments4 min readLW link

Ex­plor­ing the Re­spon­si­ble Path to AI Re­search in the Philippines

MiguelDevAug 23, 2023, 8:44 AM
6 points
0 comments6 min readLW link

[Question] Do agents with (mu­tu­ally known) iden­ti­cal util­ity func­tions but ir­rec­on­cilable knowl­edge some­times fight?

mako yassAug 23, 2023, 8:13 AM
14 points
13 comments1 min readLW link

South Bay ACX/​SSC Fall Mee­tups Everywhere

allisonaAug 23, 2023, 3:00 AM
3 points
0 comments1 min readLW link

Separate the truth from your wishes

Jacob G-WAug 23, 2023, 12:52 AM
6 points
3 comments1 min readLW link
(jacobgw.com)

Im­pli­ca­tions of ev­i­den­tial co­op­er­a­tion in large worlds

Lukas FinnvedenAug 23, 2023, 12:43 AM
39 points
4 comments17 min readLW link
(lukasfinnveden.substack.com)

South Bay Ca­sual Group Walk

allisonaAug 22, 2023, 10:43 PM
7 points
2 comments1 min readLW link

Walk while you talk: don’t balk at “no chalk”

dkl9Aug 22, 2023, 9:27 PM
41 points
10 comments2 min readLW link
(dkl9.net)

State of Gen­er­ally Available Self-Driving

jefftkAug 22, 2023, 6:50 PM
66 points
6 comments2 min readLW link
(www.jefftk.com)

Seth Ex­plains Consciousness

Jacob FalkovichAug 22, 2023, 6:06 PM
39 points
130 comments14 min readLW link1 review
(putanumonit.com)

ChatGPT challenges the case for hu­man irrationality

Kevin DorstAug 22, 2023, 12:46 PM
3 points
10 comments7 min readLW link
(kevindorst.substack.com)

[Question] Does one have rea­son to be­lieve the simu­la­tion hy­poth­e­sis is prob­a­bly true?

kuiraAug 22, 2023, 8:34 AM
1 point
20 comments1 min readLW link

The Joan of Arc Challenge For Ob­jec­tive List The­ory

Bentham's BulldogAug 22, 2023, 8:01 AM
−2 points
4 comments10 min readLW link

The Lop­sided Lives Ar­gu­ment For He­donism About Well-being

Bentham's BulldogAug 22, 2023, 7:59 AM
−2 points
8 comments22 min readLW link

Causal­ity and a Cost Se­man­tics for Neu­ral Networks

scottviteriAug 21, 2023, 9:02 PM
22 points
1 comment1 min readLW link

Ideas for im­prov­ing epistemics in AI safety outreach

micAug 21, 2023, 7:55 PM
64 points
6 comments3 min readLW link

Rice’s The­o­rem says that AIs can’t de­ter­mine much from study­ing AI source code

Michael Weiss-MalikAug 21, 2023, 7:05 PM
−12 points
4 comments1 min readLW link

Large Lan­guage Models will be Great for Censorship

Ethan EdwardsAug 21, 2023, 7:03 PM
185 points
14 comments8 min readLW link
(ethanedwards.substack.com)

“Throw­ing Ex­cep­tions” Is A Strange Pro­gram­ming Pattern

Thoth HermesAug 21, 2023, 6:50 PM
−2 points
13 comments6 min readLW link
(thothhermes.substack.com)

[Question] Which pos­si­ble AI sys­tems are rel­a­tively safe?

Zach Stein-PerlmanAug 21, 2023, 5:00 PM
42 points
20 comments1 min readLW link

Self-shut­down AI

Jan BetleyAug 21, 2023, 4:48 PM
13 points
2 comments2 min readLW link

Con­tex­tual Trans­la­tions—At­tempt 1

Varshul GuptaAug 21, 2023, 2:30 PM
−1 points
0 comments2 min readLW link
(dubverseblack.substack.com)

DIY De­liber­ate Practice

lynettebyeAug 21, 2023, 12:22 PM
63 points
4 comments5 min readLW link
(lynettebye.com)

Down­stairs Open­ing: 2br Apartment

jefftkAug 21, 2023, 12:50 AM
8 points
2 comments3 min readLW link
(www.jefftk.com)

Effi­ciency and re­source use scal­ing parity

Ege ErdilAug 21, 2023, 12:18 AM
51 points
1 comment4 min readLW link1 review

Ruin­ing an ex­pected-log-money maximizer

philhAug 20, 2023, 9:20 PM
33 points
33 comments1 min readLW link1 review
(reasonableapproximation.net)

Steven Wolfram on AI Alignment

Bill BenzonAug 20, 2023, 7:49 PM
66 points
15 comments4 min readLW link

[Question] What value does per­sonal pre­dic­tion track­ing have?

fxAug 20, 2023, 6:43 PM
7 points
3 comments1 min readLW link

Jan Kul­veit’s Cor­rigi­bil­ity Thoughts Distilled

brookAug 20, 2023, 5:52 PM
22 points
1 comment5 min readLW link

Memetic Judo #3: The In­tel­li­gence of Stochas­tic Par­rots v.2

Max TKAug 20, 2023, 3:18 PM
8 points
33 comments6 min readLW link

ACX/​SSC Boulder meetup- Septem­ber 23

Josh SacksAug 20, 2023, 2:16 PM
1 point
4 comments1 min readLW link

“Dirty con­cepts” in AI al­ign­ment dis­courses, and some guesses for how to deal with them

Aug 20, 2023, 9:13 AM
66 points
4 comments3 min readLW link

Call for Papers on Global AI Gover­nance from the UN

Chris_LeongAug 20, 2023, 8:56 AM
19 points
0 commentsLW link
(www.linkedin.com)

How do I read things on the internet

Vlad SitaloAug 20, 2023, 5:43 AM
16 points
2 comments8 min readLW link
(vlad.roam.garden)

AI Fore­cast­ing: Two Years In

jsteinhardtAug 19, 2023, 11:40 PM
72 points
15 comments11 min readLW link
(bounded-regret.ghost.io)

Four man­age­ment/​lead­er­ship book summaries

Nikola JurkovicAug 19, 2023, 11:38 PM
25 points
2 comments7 min readLW link

In­ter­pret­ing a di­men­sion­al­ity re­duc­tion of a col­lec­tion of ma­tri­ces as two pos­i­tive semidefinite block di­ag­o­nal matrices

Joseph Van NameAug 19, 2023, 7:52 PM
16 points
2 comments5 min readLW link

Will AI kill ev­ery­one? Here’s what the god­fathers of AI have to say [RA video]

WriterAug 19, 2023, 5:29 PM
58 points
8 commentsLW link
(youtu.be)

Ten vari­a­tions on red-pill-blue-pill

Richard_KennawayAug 19, 2023, 4:34 PM
23 points
34 comments3 min readLW link

Are we run­ning out of new mu­sic/​movies/​art from a meta­phys­i­cal per­spec­tive? (up­dated)

stephen_sAug 19, 2023, 4:24 PM
4 points
23 comments1 min readLW link

[Question] Any ideas for a pre­dic­tion mar­ket ob­serv­able that quan­tifies “cul­ture-wari­sa­tion”?

PpauAug 19, 2023, 3:11 PM
6 points
1 comment1 min readLW link

[Question] Clar­ify­ing how mis­al­ign­ment can arise from scal­ing LLMs

UtilAug 19, 2023, 2:16 PM
3 points
1 comment1 min readLW link

Chess as a case study in hid­den ca­pa­bil­ities in ChatGPT

AdamYedidiaAug 19, 2023, 6:35 AM
47 points
32 comments6 min readLW link