All20052006200720082009201020112012201320142015201620172018201920202021202220232024
AllJanFebMarAprMayJunJulAugSepOctNovDec
All12345678910111213141516171819202122232425262728293031

[Question] Which ra­tio­nal­ity posts are beg­ging for fur­ther prac­ti­cal de­vel­op­ment?

LoganStrohl23 Jul 2023 22:22 UTC
60 points
17 comments1 min readLW link

Please speak unpredictably

dkl923 Jul 2023 22:09 UTC
10 points
16 comments1 min readLW link
(dkl9.net)

QAPR 5: grokking is maybe not *that* big a deal?

Quintin Pope23 Jul 2023 20:14 UTC
114 points
15 comments9 min readLW link

My fa­vorite AI gov­er­nance re­search this year so far

Zach Stein-Perlman23 Jul 2023 16:30 UTC
26 points
1 comment7 min readLW link
(blog.aiimpacts.org)

“Jus­tice, Cher­ryl.”

Zack_M_Davis23 Jul 2023 16:16 UTC
85 points
21 comments9 min readLW link1 review

Sup­ple­men­tary Align­ment In­sights Through a Highly Con­trol­led Shut­down Incentive

Justausername23 Jul 2023 16:08 UTC
4 points
1 comment3 min readLW link

Au­to­g­y­nephilia dis­course is so ab­surdly bad on all sides

tailcalled23 Jul 2023 13:12 UTC
44 points
24 comments2 min readLW link

Ex­am­ples of Prompts that Make GPT-4 Out­put Falsehoods

scasper and Luke Bailey
22 Jul 2023 20:21 UTC
21 points
5 comments6 min readLW link

Think like a con­sul­tant not a salesperson

Adam Zerner22 Jul 2023 19:31 UTC
16 points
5 comments2 min readLW link

Op­ti­miza­tion, loss set at var­i­ance in RL

Clairstan22 Jul 2023 18:25 UTC
1 point
1 comment3 min readLW link

Com­pute Thresh­olds: pro­posed rules to miti­gate risk of a “lab leak” ac­ci­dent dur­ing AI train­ing runs

davidad22 Jul 2023 18:09 UTC
80 points
2 comments2 min readLW link

Apollo Neuro Fol­low Up

Elizabeth22 Jul 2023 17:20 UTC
28 points
0 comments1 min readLW link
(acesounderglass.com)

Ex­pert trap – Ways out (Part 3 of 3)

Paweł Sysiak22 Jul 2023 13:06 UTC
4 points
0 comments9 min readLW link

GPTs’ abil­ity to keep a se­cret is weirdly prompt-dependent

Mateusz Bagiński, Filip Sondej and Marcel Windys
22 Jul 2023 12:21 UTC
31 points
0 comments9 min readLW link

Re­plac­ing the Big Air Purifier

jefftk22 Jul 2023 12:10 UTC
10 points
0 comments1 min readLW link
(www.jefftk.com)

[Question] I’m con­sis­tently over­whelmed by ba­sic obli­ga­tions. Are there any paradigm shifts or other ra­tio­nal­ity-based tips that would be helpful?

Benjamin Hendricks21 Jul 2023 21:10 UTC
66 points
40 comments2 min readLW link

Fun­da­men­tally Fuzzy Con­cepts Can’t Have Crisp Defi­ni­tions: Co­op­er­a­tion and Align­ment vs Math and Physics

VojtaKovarik21 Jul 2023 21:03 UTC
12 points
18 comments3 min readLW link

Cook­ing Air Quality

jefftk21 Jul 2023 19:30 UTC
16 points
1 comment2 min readLW link
(www.jefftk.com)

Re­ward Hack­ing from a Causal Perspective

tom4everitt, Francis Rhys Ward, sbenthall, James Fox, mattmacdermott and RyanCarey
21 Jul 2023 18:27 UTC
29 points
6 comments7 min readLW link

News : Bi­den-⁠Har­ris Ad­minis­tra­tion Se­cures Vol­un­tary Com­mit­ments from Lead­ing Ar­tifi­cial In­tel­li­gence Com­pa­nies to Man­age the Risks Posed by AI

Jonathan Claybrough21 Jul 2023 18:00 UTC
65 points
10 comments2 min readLW link
(www.whitehouse.gov)

The UAP Dis­clo­sure Act of 2023 and its implications

andeslodes21 Jul 2023 17:21 UTC
36 points
47 comments20 min readLW link
(www.congress.gov)

To use com­put­ers well, learn their rules

dkl921 Jul 2023 17:00 UTC
4 points
6 comments4 min readLW link
(dkl9.net)

BCIs and the ecosys­tem of mod­u­lar minds

beren21 Jul 2023 15:58 UTC
88 points
14 comments11 min readLW link

Pri­ori­ties for the UK Foun­da­tion Models Taskforce

Andrea_Miotti21 Jul 2023 15:23 UTC
105 points
4 comments5 min readLW link
(www.conjecture.dev)

Train­ing Pro­cess Trans­parency through Gra­di­ent In­ter­pretabil­ity: Early ex­per­i­ments on toy lan­guage models

robertzk and evhub
21 Jul 2023 14:52 UTC
56 points
1 comment1 min readLW link

[Question] Can AI Align­ment please cre­ate a Red­dit-like plat­form that would make it much eas­ier for al­ign­ment re­searchers to find and help each other?

Georgeo5721 Jul 2023 14:03 UTC
−5 points
2 comments1 min readLW link

Case for Foun­da­tion Models be­yond English

Varshul Gupta21 Jul 2023 13:59 UTC
1 point
0 comments3 min readLW link
(dubverseblack.substack.com)

Meta is hiring for LLM red team­ing position

Michael Tontchev21 Jul 2023 13:57 UTC
7 points
0 comments1 min readLW link
(us.meta.talentnet.community)

[Linkpost] In­ter­pret­ing Mul­ti­modal Video Trans­form­ers Us­ing Brain Recordings

Bogdan Ionut Cirstea21 Jul 2023 11:26 UTC
5 points
0 comments1 min readLW link

Ber­lin AI Align­ment Open Meetup Au­gust 2023

GuyP21 Jul 2023 10:58 UTC
1 point
0 comments1 min readLW link

De­cod­ing in­ter­me­di­ate ac­ti­va­tions in llama-2-7b

Nina Panickssery21 Jul 2023 5:35 UTC
37 points
3 comments4 min readLW link

GPT-2′s po­si­tional em­bed­ding ma­trix is a helix

AdamYedidia21 Jul 2023 4:16 UTC
44 points
21 comments4 min readLW link

Prob­lems with pre­dic­tive his­tory classes

dkl920 Jul 2023 23:28 UTC
15 points
5 comments1 min readLW link

An­nounce­ment: AI Nar­ra­tions Available for All New LessWrong Posts

Solenoid_Entity, Ruby, Raemon, PeterH and TYPE III AUDIO
20 Jul 2023 22:17 UTC
71 points
28 comments1 min readLW link

AI #21: The Cup Overfloweth

Zvi20 Jul 2023 21:30 UTC
47 points
4 comments64 min readLW link
(thezvi.wordpress.com)

All AGI Safety ques­tions wel­come (es­pe­cially ba­sic ones) [July 2023]

smallsilo20 Jul 2023 20:20 UTC
38 points
40 comments2 min readLW link
(forum.effectivealtruism.org)

Growth of Publi­cly Available Ge­netic Se­quenc­ing Data

jefftk20 Jul 2023 19:50 UTC
11 points
2 comments1 min readLW link
(www.jefftk.com)

Progress links and tweets, 2023-07-20: “A god­dess en­throned on a car”

jasoncrawford20 Jul 2023 18:28 UTC
12 points
4 comments2 min readLW link
(rootsofprogress.org)

Boundary Place­ment Rebellion

tailcalled20 Jul 2023 17:40 UTC
54 points
21 comments12 min readLW link

Go­ing Beyond Lin­ear Mode Con­nec­tivity: The Lay­er­wise Lin­ear Fea­ture Connectivity

zhanpeng_zhou20 Jul 2023 17:38 UTC
22 points
13 comments3 min readLW link
(openreview.net)

Even Su­per­hu­man Go AIs Have Sur­pris­ing Failure Modes

AdamGleave, EuanMcLean, Tony Wang, Kellin Pelrine, Tom Tseng, Yawen Duan, Joseph Miller and MichaelDennis
20 Jul 2023 17:31 UTC
129 points
22 comments10 min readLW link
(far.ai)

Paper di­ges­tion: “May We Have Your At­ten­tion Please? Hu­man-Rights NGOs and the Prob­lem of Global Com­mu­ni­ca­tion”

Klara Helene Nielsen20 Jul 2023 17:08 UTC
4 points
1 comment2 min readLW link
(journals.sagepub.com)

The (short) case for pre­dict­ing what Aliens value

Jim Buhler20 Jul 2023 15:25 UTC
14 points
5 comments3 min readLW link

Does Cir­cuit Anal­y­sis In­ter­pretabil­ity Scale? Ev­i­dence from Mul­ti­ple Choice Ca­pa­bil­ities in Chinchilla

Neel Nanda, Tom Lieberum, Matthew Rahtz, János Kramár, Geoffrey Irving, Rohin Shah and Vlad Mikulik
20 Jul 2023 10:50 UTC
44 points
3 comments2 min readLW link
(arxiv.org)

Spec­u­la­tive in­fer­ences about path de­pen­dence in LLM su­per­vised fine-tun­ing from re­sults on lin­ear mode con­nec­tivity and model souping

RobertKirk20 Jul 2023 9:56 UTC
39 points
2 comments5 min readLW link

A case for ga­mete per­son­hood (re­duc­tio ad ab­sur­dum)

Ansyn131220 Jul 2023 8:25 UTC
−1 points
4 comments1 min readLW link

Con­tra Con­tra the So­cial Model of Disability

DirectedEvolution20 Jul 2023 6:59 UTC
20 points
22 comments16 min readLW link

[Question] Do you speed up ca­pa­bil­ities when you do AI in­te­gra­tions and con­sume over­hangs?

Michael Tontchev20 Jul 2023 6:40 UTC
6 points
1 comment1 min readLW link

[Question] How nec­es­sary is in­tu­ition, for ad­vanced math?

Nicholas / Heather Kross20 Jul 2023 0:18 UTC
11 points
8 comments1 min readLW link

Pro­ject Lawful Au­dio­book: An Unoffi­cial Fan Pro­duc­tion with ElevenLabs AI

Askwho19 Jul 2023 23:34 UTC
22 points
3 comments1 min readLW link
(askwhocastsai.substack.com)