A differ­ent ob­ser­va­tion of Vav­ilov Day

ElizabethJan 26, 2023, 9:50 PM
30 points
1 comment1 min readLW link
(acesounderglass.com)

All AGI Safety ques­tions wel­come (es­pe­cially ba­sic ones) [~monthly thread]

Jan 26, 2023, 9:01 PM
39 points
81 comments2 min readLW link

Just an­other thought ex­per­i­ment

Bohdan Kudlai Jan 26, 2023, 7:29 PM
−11 points
0 comments1 min readLW link

Exquisite Or­a­cle: A Dadaist-In­spired Liter­ary Game for Many Friends (or 1 AI)

YitzJan 26, 2023, 6:26 PM
6 points
1 comment1 min readLW link

AI Risk Man­age­ment Frame­work | NIST

DragonGodJan 26, 2023, 3:27 PM
36 points
4 comments2 min readLW link
(www.nist.gov)

“How to Es­cape from the Si­mu­la­tion”—Seeds of Science call for reviewers

rogersbaconJan 26, 2023, 3:11 PM
12 points
0 comments1 min readLW link

Loom: Why and How to use it

brookJan 26, 2023, 2:34 PM
2 points
5 commentsLW link

Covid 1/​26/​23: Case Count Crash

ZviJan 26, 2023, 12:50 PM
32 points
5 comments9 min readLW link
(thezvi.wordpress.com)

[Question] How are you cur­rently mod­el­ing COVID con­ta­gious­ness?

CounterBlunderJan 26, 2023, 4:46 AM
2 points
2 comments1 min readLW link

[Question] What’s the sim­plest con­crete un­solved prob­lem in AI al­ign­ment?

aggJan 26, 2023, 4:15 AM
28 points
4 comments1 min readLW link

2022 Less Wrong Cen­sus/​Sur­vey: Re­quest for Comments

ScrewtapeJan 25, 2023, 8:57 PM
5 points
29 comments1 min readLW link

Next steps af­ter AGISF at UMich

JakubKJan 25, 2023, 8:57 PM
10 points
0 comments5 min readLW link
(docs.google.com)

AGI will have learnt util­ity functions

berenJan 25, 2023, 7:42 PM
38 points
4 comments13 min readLW link

[RFC] Pos­si­ble ways to ex­pand on “Dis­cov­er­ing La­tent Knowl­edge in Lan­guage Models Without Su­per­vi­sion”.

Jan 25, 2023, 7:03 PM
48 points
6 comments12 min readLW link

Spread­ing mes­sages to help with the most im­por­tant century

HoldenKarnofskyJan 25, 2023, 6:20 PM
75 points
4 comments18 min readLW link
(www.cold-takes.com)

My Model Of EA Burnout

LoganStrohlJan 25, 2023, 5:52 PM
259 points
50 comments5 min readLW link1 review

Thoughts on the im­pact of RLHF research

paulfchristianoJan 25, 2023, 5:23 PM
253 points
102 comments9 min readLW link

[Question] Could AI be used to en­g­ineer a so­ciopoli­ti­cal situ­a­tion where hu­mans can solve the prob­lems sur­round­ing AGI?

hollowingJan 25, 2023, 5:17 PM
1 point
6 comments1 min readLW link

Progress links and tweets, 2023-01-25

jasoncrawfordJan 25, 2023, 4:12 PM
8 points
0 comments1 min readLW link
(rootsofprogress.org)

Vi­su­al­i­sa­tion of Prob­a­bil­ity Mass

brookJan 25, 2023, 3:09 PM
7 points
0 commentsLW link

When Did EA Start?

jefftkJan 25, 2023, 2:30 PM
37 points
2 comments2 min readLW link
(www.jefftk.com)

Some Thoughts on AI Art

abramdemskiJan 25, 2023, 2:18 PM
74 points
20 comments7 min readLW link

Quick thoughts on “scal­able over­sight” /​ “su­per-hu­man feed­back” research

David Scott Krueger (formerly: capybaralet)Jan 25, 2023, 12:55 PM
27 points
9 comments2 min readLW link

Sapir-Whorf for Rationalists

Duncan Sabien (Inactive)Jan 25, 2023, 7:58 AM
155 points
49 comments19 min readLW link

ChatGPT vs the 2-4-6 Task

cwilluJan 25, 2023, 6:59 AM
20 points
4 comments3 min readLW link

Pes­simistic Shard Theory

Garrett BakerJan 25, 2023, 12:59 AM
72 points
13 comments3 min readLW link

Thatcher’s Axiom

Edward P. KöningsJan 24, 2023, 10:35 PM
10 points
22 comments4 min readLW link

[Question] Some ques­tions about free will compatibilism

Asking QuestionsJan 24, 2023, 9:54 PM
3 points
21 comments6 min readLW link

Alexan­der and Yud­kowsky on AGI goals

Jan 24, 2023, 9:09 PM
179 points
53 comments26 min readLW link1 review

[Question] Is _The Age of AI: And Our Hu­man Fu­ture_ worth reading

jmhJan 24, 2023, 9:05 PM
4 points
0 comments1 min readLW link

In­verse Scal­ing Prize: Se­cond Round Winners

Jan 24, 2023, 8:12 PM
58 points
17 comments15 min readLW link

ChatGPT in­ti­mates a tan­ta­l­iz­ing fu­ture; its core LLM is or­ga­nized on mul­ti­ple lev­els; and it has bro­ken the idea of think­ing.

Bill BenzonJan 24, 2023, 7:05 PM
5 points
0 comments5 min readLW link

How-to Trans­former Mechanis­tic In­ter­pretabil­ity—in 50 lines of code or less!

StefanHexJan 24, 2023, 6:45 PM
47 points
5 comments13 min readLW link

The Cabi­net of Wikipe­dian Curiosities

Sam EnrightJan 24, 2023, 6:22 PM
36 points
5 comments6 min readLW link
(samenright.com)

Ex­plana­tory Par­si­mony, Ex­plana­tory Su­perflu­ous­ness and Use­less­ness of New­ton’s First Law

Jimdrix_HendriJan 24, 2023, 5:21 PM
−2 points
7 comments2 min readLW link

Guessti­mate: Why and how to use it

Jan 24, 2023, 4:24 PM
8 points
0 comments3 min readLW link
(forum.effectivealtruism.org)

GWWC Pledge History

jefftkJan 24, 2023, 3:50 PM
15 points
0 comments3 min readLW link
(www.jefftk.com)

Gra­di­ent hack­ing is ex­tremely difficult

berenJan 24, 2023, 3:45 PM
170 points
22 comments5 min readLW link

[Question] What sci-fi books are most rele­vant to a fu­ture with trans­for­ma­tive AI?

sidJan 24, 2023, 3:30 PM
2 points
9 comments1 min readLW link

Grant-mak­ing in EA should con­sider peer-re­view­ing grant ap­pli­ca­tions along the pub­lic-sec­tor model

Ben SmithJan 24, 2023, 3:01 PM
0 points
3 commentsLW link

“Endgame safety” for AGI

Steven ByrnesJan 24, 2023, 2:15 PM
85 points
10 comments6 min readLW link

Thoughts on hard­ware /​ com­pute re­quire­ments for AGI

Steven ByrnesJan 24, 2023, 2:03 PM
63 points
32 comments24 min readLW link

Pa­ram­e­ter Scal­ing Comes for RL, Maybe

1a3ornJan 24, 2023, 1:55 PM
100 points
3 comments14 min readLW link

How to find cool things in a new place

Sam F. BrownJan 24, 2023, 11:20 AM
12 points
0 comments1 min readLW link

[Cross­post] ACX 2022 Pre­dic­tion Con­test Results

Jan 24, 2023, 6:56 AM
48 points
6 comments8 min readLW link

The Hu­man-AI Reflec­tive Equilibrium

Allison DuettmannJan 24, 2023, 1:32 AM
22 points
1 comment24 min readLW link

“Sta­tus” can be cor­ro­sive; here’s how I han­dle it

Orpheus16Jan 24, 2023, 1:25 AM
71 points
8 comments6 min readLW link

[Question] What area of the digi­tal do­main seems safe from AI in the next 5-10 years?

Adrien ChauvetJan 24, 2023, 1:16 AM
11 points
14 comments1 min readLW link

Some of my dis­agree­ments with List of Lethalities

TurnTroutJan 24, 2023, 12:25 AM
70 points
7 comments10 min readLW link

Round­ing Some­one Off

David UdellJan 24, 2023, 12:03 AM
25 points
0 comments5 min readLW link