Shut­ting Down the Light­cone Offices

Mar 14, 2023, 10:47 PM
338 points
103 comments17 min readLW link2 reviews

[Question] What are some ideas that LessWrong has rein­vented?

RomanHaukssonMar 14, 2023, 10:27 PM
4 points
13 comments1 min readLW link

Hu­man prefer­ences as RL critic val­ues—im­pli­ca­tions for alignment

Seth HerdMar 14, 2023, 10:10 PM
26 points
6 comments6 min readLW link

Paper­clipGPT(-4)

Michael TontchevMar 14, 2023, 10:03 PM
7 points
0 comments11 min readLW link

GPT-4 de­vel­oper livestream

Gerald MonroeMar 14, 2023, 8:55 PM
9 points
0 comments1 min readLW link
(www.youtube.com)

[Question] Main ac­tors in the AI race

MartaMar 14, 2023, 8:50 PM
3 points
1 comment1 min readLW link

Suc­cess with­out dig­nity: a nearcast­ing story of avoid­ing catas­tro­phe by luck

HoldenKarnofskyMar 14, 2023, 7:23 PM
76 points
17 comments15 min readLW link

GPT can write Quines now (GPT-4)

Andrew_CritchMar 14, 2023, 7:18 PM
112 points
30 comments1 min readLW link

Vec­tor se­man­tics and the (in-con­text) con­struc­tion of mean­ing in Col­eridge’s “Kubla Khan”

Bill BenzonMar 14, 2023, 7:16 PM
4 points
0 comments7 min readLW link

A bet­ter anal­ogy and ex­am­ple for teach­ing AI takeover: the ML Inferno

Christopher KingMar 14, 2023, 7:14 PM
18 points
0 comments5 min readLW link

PaLM API & MakerSuite

Gabe MMar 14, 2023, 7:08 PM
20 points
1 comment1 min readLW link
(developers.googleblog.com)

What is a defi­ni­tion, how can it be ex­trap­o­lated?

Stuart_ArmstrongMar 14, 2023, 6:08 PM
34 points
5 comments7 min readLW link

Cam­bridge LW: Ra­tion­al­ity Prac­tice: The Map is Not the Territory

DarmaniMar 14, 2023, 5:56 PM
6 points
0 comments1 min readLW link

[Question] Benefi­cial ini­tial con­di­tions for AGI

mikbpMar 14, 2023, 5:41 PM
1 point
3 comments1 min readLW link

[Question] “The elephant in the room: the biggest risk of ar­tifi­cial in­tel­li­gence may not be what we think” What to say about that?

Obladi ObladaMar 14, 2023, 5:37 PM
−5 points
0 comments3 min readLW link

GPT-4

nzMar 14, 2023, 5:02 PM
151 points
150 comments1 min readLW link
(openai.com)

Sto­ry­tel­ling Makes GPT-3.5 Deon­tol­o­gist: Un­ex­pected Effects of Con­text on LLM Behavior

Mar 14, 2023, 8:44 AM
17 points
0 comments12 min readLW link

Fore­cast­ing Author­i­tar­ian and Sovereign Power uses of Large Lan­guage Models

K. Liam SmithMar 14, 2023, 8:44 AM
7 points
0 comments8 min readLW link
(taboo.substack.com)

Fixed points in mor­tal pop­u­la­tion games

ViktoriaMalyasovaMar 14, 2023, 7:10 AM
31 points
0 comments12 min readLW link
(www.lesswrong.com)

To de­ter­mine al­ign­ment difficulty, we need to know the ab­solute difficulty of al­ign­ment generalization

Jeffrey LadishMar 14, 2023, 3:52 AM
12 points
3 comments2 min readLW link

EA & LW Fo­rum Weekly Sum­mary (6th − 12th March 2023)

Zoe WilliamsMar 14, 2023, 3:01 AM
7 points
0 commentsLW link

Al­paca: A Strong Open-Source In­struc­tion-Fol­low­ing Model

sanxiynMar 14, 2023, 2:41 AM
26 points
2 comments1 min readLW link
(crfm.stanford.edu)

Dis­cus­sion with Nate Soares on a key al­ign­ment difficulty

HoldenKarnofskyMar 13, 2023, 9:20 PM
267 points
43 comments22 min readLW link1 review

What Dis­cov­er­ing La­tent Knowl­edge Did and Did Not Find

Fabien RogerMar 13, 2023, 7:29 PM
166 points
17 comments11 min readLW link

South Bay ACX/​LW Meetup

ISMar 13, 2023, 6:25 PM
2 points
0 comments1 min readLW link

Could Roko’s basilisk acausally bar­gain with a pa­per­clip max­i­mizer?

Christopher KingMar 13, 2023, 6:21 PM
1 point
8 comments1 min readLW link

Bayesian op­ti­miza­tion to find molecules that bind to proteins

rotatingpaguroMar 13, 2023, 6:17 PM
1 point
0 comments1 min readLW link
(www.youtube.com)

Linkpost: ‘Dis­solv­ing’ AI Risk – Pa­ram­e­ter Uncer­tainty in AI Fu­ture Forecasting

DavidWMar 13, 2023, 4:52 PM
6 points
0 comments1 min readLW link
(forum.effectivealtruism.org)

De­cen­tral­ized Exclusion

jefftkMar 13, 2023, 3:50 PM
26 points
19 comments2 min readLW link
(www.jefftk.com)

Linkpost: A Con­tra AI FOOM Read­ing List

DavidWMar 13, 2023, 2:45 PM
25 points
4 comments1 min readLW link
(magnusvinding.com)

Linkpost: A tale of 2.5 or­thog­o­nal­ity theses

DavidWMar 13, 2023, 2:19 PM
9 points
3 comments1 min readLW link
(forum.effectivealtruism.org)

Plan for mediocre al­ign­ment of brain-like [model-based RL] AGI

Steven ByrnesMar 13, 2023, 2:11 PM
68 points
25 comments12 min readLW link

Against AGI Timelines

Jonathan YanMar 13, 2023, 1:33 PM
13 points
3 comments1 min readLW link
(benlandautaylor.com)

What is cal­ibra­tion?

AlexMennenMar 13, 2023, 6:30 AM
27 points
1 comment4 min readLW link

On tak­ing AI risk se­ri­ously

Eleni AngelouMar 13, 2023, 5:50 AM
6 points
0 comments1 min readLW link
(www.nytimes.com)

Nose /​ throat treat­ments for res­pi­ra­tory infections

juliawiseMar 13, 2023, 2:41 AM
47 points
6 comments8 min readLW link

Gold, Silver, Red: A color scheme for un­der­stand­ing people

Michael SoareverixMar 13, 2023, 1:06 AM
17 points
2 comments4 min readLW link

Yud­kowsky on AGI risk on the Ban­kless podcast

Rob BensingerMar 13, 2023, 12:42 AM
83 points
5 commentsLW link

Thoughts on self-in­spect­ing neu­ral net­works.

DeruwynMar 12, 2023, 11:58 PM
4 points
2 comments5 min readLW link

An AI risk ar­gu­ment that res­onates with NYTimes readers

Julian BradshawMar 12, 2023, 11:09 PM
212 points
14 comments1 min readLW link

Mu­si­ci­ans and Mouths

jefftkMar 12, 2023, 10:50 PM
13 points
7 comments2 min readLW link
(www.jefftk.com)

Are there cog­ni­tive realms?

TsviBTMar 12, 2023, 7:28 PM
34 points
3 comments10 min readLW link1 review

[Question] What hap­pened on the Ex­tropi­ans mes­sage board?

politicalpersuasionMar 12, 2023, 7:22 PM
−53 points
1 comment1 min readLW link

Creat­ing a Dis­cord server for Mechanis­tic In­ter­pretabil­ity Projects

Victor LevosoMar 12, 2023, 6:00 PM
30 points
6 comments2 min readLW link

Paper Repli­ca­tion Walk­through: Re­v­erse-Eng­ineer­ing Mo­du­lar Addition

Neel NandaMar 12, 2023, 1:25 PM
18 points
0 comments1 min readLW link
(neelnanda.io)

What prob­lems do Afri­can-Amer­i­cans face? An ini­tial in­ves­ti­ga­tion us­ing Stand­point Episte­mol­ogy and Surveys

tailcalledMar 12, 2023, 11:42 AM
34 points
26 comments15 min readLW link

“Liquidity” vs “solvency” in bank runs (and some notes on Sili­con Valley Bank)

rossryMar 12, 2023, 9:16 AM
108 points
27 comments12 min readLW link

“You’ll Never Per­suade Peo­ple Like That”

Zack_M_DavisMar 12, 2023, 5:38 AM
18 points
31 comments2 min readLW link

Par­a­sitic Lan­guage Games: main­tain­ing am­bi­guity to hide con­flict while burn­ing the commons

HazardMar 12, 2023, 5:25 AM
115 points
17 comments13 min readLW link

[Question] Is there a way to sort LW search re­sults by date posted?

zeshenMar 12, 2023, 4:56 AM
5 points
1 comment1 min readLW link