Con­sider Try­ing Dictation

jefftkJan 22, 2023, 10:50 PM
23 points
10 comments2 min readLW link
(www.jefftk.com)

Emo­tional at­tach­ment to AIs opens doors to problems

Igor IvanovJan 22, 2023, 8:28 PM
20 points
10 comments4 min readLW link

What fills a vac­uum?

Logan KiellerJan 22, 2023, 7:25 PM
11 points
6 comments2 min readLW link

Gem­ini mod­el­ing

TsviBTJan 22, 2023, 2:28 PM
12 points
8 comments11 min readLW link

Large lan­guage mod­els learn to rep­re­sent the world

gjmJan 22, 2023, 1:10 PM
101 points
20 comments3 min readLW link1 review

Quan­tum Suicide, De­ci­sion The­ory, and The Multiverse

SlimepriestessJan 22, 2023, 8:44 AM
7 points
39 comments10 min readLW link
(voidgoddess.org)

NYT: Google will “re­cal­ibrate” the risk of re­leas­ing AI due to com­pe­ti­tion with OpenAI

Michael HuangJan 22, 2023, 8:38 AM
47 points
2 comments1 min readLW link
(www.nytimes.com)

[Question] Just don’t make a util­ity max­i­mizer?

FinalFormal2Jan 22, 2023, 6:33 AM
−1 points
10 comments1 min readLW link

A “su­per-in­tel­li­gence” un­in­tended con­se­quences “pre­serve life” scenario

Program DenJan 22, 2023, 4:38 AM
−12 points
0 comments1 min readLW link

How Do We Pro­tect AI From Hu­mans?

Alex BeymanJan 22, 2023, 3:59 AM
−4 points
11 comments6 min readLW link

To Ques­tion God

Collapse KittyJan 22, 2023, 3:51 AM
8 points
2 comments3 min readLW link

Some­what-Brief thoughts on rea­son­able­ness of conspiracy

grabbagJan 22, 2023, 3:50 AM
−14 points
16 comments5 min readLW link

Bioin­for­mat­ics 101

iy3dJan 22, 2023, 2:36 AM
5 points
0 comments4 min readLW link

South Bay ACX/​LW Meetup

ISJan 22, 2023, 1:42 AM
3 points
1 comment1 min readLW link

Rock, Paper and Scis­sors: A Game The­ory View

Edward P. KöningsJan 21, 2023, 9:00 PM
18 points
3 comments4 min readLW link
(edwardknings.substack.com)

A new Heuris­tic to Up­date on the Cre­dences of Others

aaron_maiJan 21, 2023, 9:00 PM
6 points
0 comments20 min readLW link

AI Safety “Text­book”. Test chap­ter. Orthog­o­nal­ity Th­e­sis, Good­hart Law and In­stru­men­tal Convergency

Jan 21, 2023, 6:13 PM
4 points
0 comments12 min readLW link

[Linkpost] TIME ar­ti­cle: Deep­Mind’s CEO Helped Take AI Main­stream. Now He’s Urg­ing Caution

Orpheus16Jan 21, 2023, 4:51 PM
58 points
2 comments3 min readLW link
(time.com)

Small Go Boards

jefftkJan 21, 2023, 2:50 PM
18 points
6 comments2 min readLW link
(www.jefftk.com)

[Question] Why are we so illog­i­cal?

Program DenJan 21, 2023, 8:28 AM
−25 points
0 comments1 min readLW link

An­nounc­ing aisafety.training

JJ HepburnJan 21, 2023, 1:01 AM
61 points
4 comments1 min readLW link

Why real es­tate is the only in­vest­ment that mat­ters in AI dom­i­nated future

GJan 20, 2023, 7:40 PM
7 points
10 comments1 min readLW link

Tran­script of Sam Alt­man’s in­ter­view touch­ing on AI safety

Andy_McKenzieJan 20, 2023, 4:14 PM
121 points
42 comments10 min readLW link

[Question] COVID con­ta­gious­ness af­ter nega­tive tests?

wunanJan 20, 2023, 3:02 PM
10 points
2 comments1 min readLW link

Cri­tique of some re­cent philos­o­phy of LLMs’ minds

Roman LeventovJan 20, 2023, 12:53 PM
52 points
8 comments20 min readLW link

Preface

iy3dJan 20, 2023, 12:38 PM
4 points
0 comments2 min readLW link

Lost in In­no­va­tion: The Case of Phlogiston

adamShimiJan 20, 2023, 12:19 PM
19 points
8 comments4 min readLW link
(epistemologicalvigilance.substack.com)

finite, ac­tual in­finity, po­ten­tial infinity

Alok SinghJan 20, 2023, 11:00 AM
3 points
15 comments1 min readLW link
(alok.github.io)

Gen­er­al­iz­abil­ity & Hope for AI [MLAISU W03]

Esben KranJan 20, 2023, 10:06 AM
5 points
2 comments2 min readLW link
(newsletter.apartresearch.com)

What’s go­ing on with ‘crunch time’?

rosehadsharJan 20, 2023, 9:42 AM
54 points
6 comments4 min readLW link

Shard the­ory al­ign­ment has im­por­tant, of­ten-over­looked free pa­ram­e­ters.

Charlie SteinerJan 20, 2023, 9:30 AM
36 points
10 comments3 min readLW link

Solv­ing For Meta-Ethics By In­duc­ing From The Self

VisionaryHeraJan 20, 2023, 7:21 AM
4 points
1 comment9 min readLW link

Ve­gan Nutri­tion Test­ing Pro­ject: In­terim Report

ElizabethJan 20, 2023, 5:50 AM
102 points
37 comments8 min readLW link
(acesounderglass.com)

Maybe you can learn ex­otic ex­pe­riences via an­a­lyt­i­cal thought

Q HomeJan 20, 2023, 1:50 AM
2 points
6 comments15 min readLW link

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)