The Gallery for Paint­ing Trans­for­ma­tions—A GPT-3 Analogy

Robert_AIZIJan 19, 2023, 11:32 PM
1 point
0 comments6 min readLW link
(aizi.substack.com)

AGI safety field build­ing pro­jects I’d like to see

Severin T. SeehrichJan 19, 2023, 10:40 PM
68 points
28 comments9 min readLW link

Ex­ten­sion­al­ity and the uni­valence ax­iom of type theory

Thomas KehrenbergJan 19, 2023, 10:36 PM
6 points
2 comments16 min readLW link

The spiritual benefits of ma­te­rial progress

jasoncrawfordJan 19, 2023, 9:35 PM
24 points
15 comments7 min readLW link
(rootsofprogress.org)

An­nounc­ing Cavendish Labs

Jan 19, 2023, 8:15 PM
59 points
5 comments2 min readLW link
(forum.effectivealtruism.org)

Thoughts on re­fus­ing harm­ful re­quests to large lan­guage models

William_SJan 19, 2023, 7:49 PM
32 points
4 comments2 min readLW link

MA RMV Overloaded

jefftkJan 19, 2023, 4:40 PM
16 points
0 comments2 min readLW link
(www.jefftk.com)

“Hereti­cal Thoughts on AI” by Eli Dourado

DragonGodJan 19, 2023, 4:11 PM
146 points
38 comments3 min readLW link
(www.elidourado.com)

Covid 1/​19/​23: Flipped Numbers

ZviJan 19, 2023, 1:30 PM
19 points
4 comments4 min readLW link
(thezvi.wordpress.com)

List of tech­ni­cal AI safety ex­er­cises and projects

JakubKJan 19, 2023, 9:35 AM
41 points
5 comments1 min readLW link
(docs.google.com)

Group-level Con­se­quences of Psy­cholog­i­cal Problems

Jan 19, 2023, 9:27 AM
28 points
3 comments2 min readLW link

6-para­graph AI risk in­tro for MAISI

JakubKJan 19, 2023, 9:22 AM
11 points
0 comments2 min readLW link
(www.maisi.club)

200 COP in MI: Study­ing Learned Fea­tures in Lan­guage Models

Neel NandaJan 19, 2023, 3:48 AM
24 points
2 comments30 min readLW link

Ama­zon clos­ing Ama­zonSmile to fo­cus its philan­thropic giv­ing to pro­grams with greater impact

Gordon Seidoh WorleyJan 19, 2023, 1:15 AM
10 points
8 commentsLW link

Gra­di­ent Filtering

Jan 18, 2023, 8:09 PM
56 points
16 comments13 min readLW link

[Cross-post] Is the Fermi Para­dox due to the Flaw of Aver­ages?

Jan 18, 2023, 7:22 PM
41 points
27 comments15 min readLW link
(lumina.com)

First Three Epi­sodes of The Filan Cabinet

DanielFilanJan 18, 2023, 7:20 PM
17 points
1 comment1 min readLW link

[Question] Best Ques­tions To Vet Po­ten­tial Ai-Safety Applicants

jacksonjezionJan 18, 2023, 7:01 PM
6 points
1 comment1 min readLW link

[Question] Look­ing for a spe­cific group of people

FriggenRedChickenManJan 18, 2023, 7:00 PM
15 points
21 comments1 min readLW link

A prob­lem with group epistemics

Mckay JensenJan 18, 2023, 5:06 PM
4 points
4 comments3 min readLW link
(quevivasbien.github.io)

Why you should learn sign language

Noah TopperJan 18, 2023, 5:03 PM
53 points
23 comments7 min readLW link
(naivebayes.substack.com)

Fly­ing With Covid

jefftkJan 18, 2023, 5:00 PM
44 points
29 comments3 min readLW link
(www.jefftk.com)

Pro­to­type of Us­ing GPT-3 to Gen­er­ate Text­book-length Content

Rafael CosmanJan 18, 2023, 2:25 PM
2 points
8 comments40 min readLW link
(github.com)

How many peo­ple are work­ing (di­rectly) on re­duc­ing ex­is­ten­tial risk from AI?

Benjamin HiltonJan 18, 2023, 8:46 AM
20 points
1 commentLW link

EA & LW Fo­rum Sum­maries (9th Jan to 15th Jan 23′)

Zoe WilliamsJan 18, 2023, 7:29 AM
17 points
0 commentsLW link

OpenAI’s Align­ment Plan is not S.M.A.R.T.

Søren ElverlinJan 18, 2023, 6:39 AM
9 points
19 comments4 min readLW link

[Question] For­mal defi­ni­tion of On­tol­ogy Mis­match?

NathanBarnardJan 18, 2023, 5:52 AM
6 points
0 comments1 min readLW link

[Question] Trans­former Mech In­terp: Any vi­su­al­iza­tions?

Joyee ChenJan 18, 2023, 4:32 AM
3 points
0 comments1 min readLW link

Neu­ral net­works gen­er­al­ize be­cause of this one weird trick

Jesse HooglandJan 18, 2023, 12:10 AM
183 points
34 comments15 min readLW link1 review
(www.jessehoogland.com)

Progress links and tweets, 2023-01-17

jasoncrawfordJan 17, 2023, 9:31 PM
13 points
3 comments2 min readLW link
(rootsofprogress.org)

Quotes Worth Talk­ing About

akaTricksterJan 17, 2023, 9:26 PM
−1 points
0 comments3 min readLW link

Build­ing a tran­shu­man­ist fu­ture: 15 years of hplus­roadmap, now Discord

kanzureJan 17, 2023, 9:17 PM
42 points
1 comment1 min readLW link
(twitter.com)

Ad Fraud De­tec­tion Pre­dic­tion Market

jefftkJan 17, 2023, 6:10 PM
17 points
0 comments2 min readLW link
(www.jefftk.com)

Col­lin Burns on Align­ment Re­search And Dis­cov­er­ing La­tent Knowl­edge Without Supervision

Michaël TrazziJan 17, 2023, 5:21 PM
25 points
5 comments4 min readLW link
(theinsideview.ai)

Les­sons learned and re­view of the AI Safety Nudge Competition

Marc CarauleanuJan 17, 2023, 5:13 PM
3 points
0 commentsLW link

Five Rea­sons to Lie

DzoldzayaJan 17, 2023, 4:53 PM
0 points
19 comments3 min readLW link

On AI and In­ter­est Rates

ZviJan 17, 2023, 3:00 PM
79 points
13 comments8 min readLW link
(thezvi.wordpress.com)

Lan­guage mod­els can gen­er­ate su­pe­rior text com­pared to their input

ChristianKlJan 17, 2023, 10:57 AM
48 points
28 comments1 min readLW link

Löbian emo­tional pro­cess­ing of emer­gent co­op­er­a­tion: an example

Andrew_CritchJan 17, 2023, 5:59 AM
23 points
0 comments8 min readLW link

Prepar­ing for AI-as­sisted al­ign­ment re­search: we need data!

Caleb BiddulphJan 17, 2023, 3:28 AM
31 points
3 commentsLW link

Tesla Model 3 Review

jefftkJan 17, 2023, 1:10 AM
18 points
15 comments4 min readLW link
(www.jefftk.com)

[Question] Should AI writ­ers be pro­hibited in ed­u­ca­tion?

Eleni AngelouJan 17, 2023, 12:42 AM
6 points
2 comments1 min readLW link

What can thought-ex­per­i­ments do?

Cleo NardoJan 17, 2023, 12:35 AM
16 points
3 comments5 min readLW link

Ex­per­i­ment Idea: RL Agents Evad­ing Learned Shutdownability

Leon LangJan 16, 2023, 10:46 PM
31 points
7 comments17 min readLW link
(docs.google.com)

Con­se­quen­tial­ists: One-Way Pat­tern Traps

David UdellJan 16, 2023, 8:48 PM
59 points
3 comments14 min readLW link

Book Re­view: Wor­lds of Flow

rememberJan 16, 2023, 8:17 PM
83 points
3 comments9 min readLW link

For the Record: DL ∩ ASI = ∅

maximkazhenkovJan 16, 2023, 7:04 PM
13 points
13 comments2 min readLW link

[Question] What de­ter­mines fe­male ro­man­tic “mar­ket value”?

anon_girlJan 16, 2023, 6:45 PM
16 points
53 comments1 min readLW link

Sta­tus conscious

avantika.mehraJan 16, 2023, 5:44 PM
2 points
0 comments5 min readLW link

Con­fus­ing the ideal for the necessary

adamShimiJan 16, 2023, 5:29 PM
79 points
6 comments1 min readLW link
(epistemologicalvigilance.substack.com)