AGI-level rea­soner will ap­pear sooner than an agent; what the hu­man­ity will do with this rea­soner is critical

Roman LeventovJul 30, 2022, 8:56 PM
24 points
10 comments1 min readLW link

[Question] What job should I do?

Tom PaineJul 30, 2022, 9:15 AM
2 points
8 comments1 min readLW link

How trans­parency changed over time

ViktoriaMalyasovaJul 30, 2022, 4:36 AM
21 points
0 comments6 min readLW link

Trans­lat­ing be­tween La­tent Spaces

Jul 30, 2022, 3:25 AM
27 points
2 comments8 min readLW link

Drexler’s Nan­otech Forecast

PeterMcCluskeyJul 30, 2022, 12:45 AM
25 points
28 comments3 min readLW link
(www.bayesianinvestor.com)

Hu­mans Reflect­ing on HRH

leogaoJul 29, 2022, 9:56 PM
26 points
4 comments2 min readLW link

Com­par­ing Four Ap­proaches to In­ner Alignment

Lucas TeixeiraJul 29, 2022, 9:06 PM
38 points
1 comment9 min readLW link

Ques­tions for a The­ory of Narratives

Marv KJul 29, 2022, 7:31 PM
5 points
4 comments4 min readLW link

Focusing

CFAR!DuncanJul 29, 2022, 7:15 PM
114 points
23 comments14 min readLW link

Con­jec­ture: In­ter­nal In­fo­haz­ard Policy

Jul 29, 2022, 7:07 PM
131 points
6 comments19 min readLW link

Ab­stract­ing The Hard­ness of Align­ment: Un­bounded Atomic Optimization

adamShimiJul 29, 2022, 6:59 PM
72 points
3 comments16 min readLW link

Bucket Errors

CFAR!DuncanJul 29, 2022, 6:50 PM
43 points
7 comments11 min readLW link

Distil­la­tion Con­test—Re­sults and Recap

ArisJul 29, 2022, 5:40 PM
34 points
0 comments7 min readLW link

The gen­er­al­ized Sier­pin­ski-Mazurk­iewicz the­o­rem.

Donald HobsonJul 29, 2022, 12:12 AM
11 points
4 comments1 min readLW link

The Con­ver­sa­tions We Make Space For

Severin T. SeehrichJul 28, 2022, 9:37 PM
21 points
0 comments3 min readLW link

An­nounc­ing the AI Safety Field Build­ing Hub, a new effort to provide AISFB pro­jects, men­tor­ship, and funding

Vael GatesJul 28, 2022, 9:29 PM
49 points
3 comments6 min readLW link

Defin­ing Op­ti­miza­tion in a Deeper Way Part 4

J BostockJul 28, 2022, 5:02 PM
7 points
0 comments5 min readLW link

Covid 7/​28/​22: Ruin­ing It For Everyone

ZviJul 28, 2022, 3:10 PM
32 points
8 comments12 min readLW link
(thezvi.wordpress.com)

Mon­key­pox Post #2

ZviJul 28, 2022, 1:20 PM
36 points
3 comments6 min readLW link
(thezvi.wordpress.com)

For Bet­ter Com­ment­ing, Stop Out Loud

DirectedEvolutionJul 28, 2022, 1:39 AM
18 points
30 comments1 min readLW link

Seek­ing beta read­ers who are ig­no­rant of biol­ogy but knowl­edge­able about AI safety

Holly_ElmoreJul 27, 2022, 11:02 PM
11 points
6 comments1 min readLW link

Prin­ci­ples of Pri­vacy for Align­ment Research

johnswentworthJul 27, 2022, 7:53 PM
73 points
31 comments7 min readLW link

Mo­ral strate­gies at differ­ent ca­pa­bil­ity levels

Richard_NgoJul 27, 2022, 6:50 PM
112 points
14 comments5 min readLW link
(thinkingcomplete.blogspot.com)

Progress links and tweets, 2022-07-27

jasoncrawfordJul 27, 2022, 5:20 PM
18 points
0 comments1 min readLW link
(rootsofprogress.org)

Quan­tum Ad­van­tage in Learn­ing from Experiments

Dennis TowneJul 27, 2022, 3:49 PM
5 points
5 comments1 min readLW link
(ai.googleblog.com)

Levels of Pluralism

adamShimiJul 27, 2022, 9:35 AM
37 points
0 comments14 min readLW link

Hu­man tri­als for the Mar­burg vac­cine: fund­ing op­por­tu­nity?

americanwalrusJul 27, 2022, 5:53 AM
3 points
0 comments1 min readLW link
(www.independent.co.uk)

[Question] “Fa­nat­i­cal” Longter­mists: Why is Pas­cal’s Wager wrong?

YitzJul 27, 2022, 4:16 AM
3 points
7 comments1 min readLW link

Unify­ing Bar­gain­ing No­tions (2/​2)

DiffractorJul 27, 2022, 3:40 AM
118 points
19 comments21 min readLW link

AGI ruin sce­nar­ios are likely (and dis­junc­tive)

So8resJul 27, 2022, 3:21 AM
175 points
38 comments6 min readLW link

Tech­noc­racy and the Space Age

jasoncrawfordJul 26, 2022, 11:14 PM
25 points
5 comments2 min readLW link
(rootsofprogress.org)

«Boundaries», Part 1: a key miss­ing con­cept from util­ity theory

Andrew_CritchJul 26, 2022, 11:03 PM
158 points
33 comments7 min readLW link

In­co­her­ence of un­bounded selfishness

emmabJul 26, 2022, 10:27 PM
−6 points
2 comments1 min readLW link

«Boundaries» Se­quence (In­dex Post)

Andrew_CritchJul 26, 2022, 7:12 PM
25 points
1 comment1 min readLW link

Ac­tive In­fer­ence as a for­mal­i­sa­tion of in­stru­men­tal convergence

Roman LeventovJul 26, 2022, 5:55 PM
12 points
2 comments3 min readLW link
(direct.mit.edu)

NeurIPS ML Safety Work­shop 2022

Dan HJul 26, 2022, 3:28 PM
72 points
2 comments1 min readLW link
(neurips2022.mlsafety.org)

AI ethics vs AI alignment

Wei DaiJul 26, 2022, 1:08 PM
5 points
1 comment1 min readLW link

Utility func­tions and prob­a­bil­ities are entangled

Thomas KwaJul 26, 2022, 5:36 AM
15 points
5 comments1 min readLW link

How Promis­ing is The­o­ret­i­cal Re­search on Ra­tion­al­ity? Seek­ing Ca­reer Advice

Aspirant223Jul 26, 2022, 1:08 AM
3 points
3 comments3 min readLW link

Pre­dic­tion mar­kets meetup/​cowork­ing (hosted by Man­i­fold Mar­kets)

Jul 26, 2022, 12:14 AM
2 points
0 comments1 min readLW link

Align­ment be­ing im­pos­si­ble might be bet­ter than it be­ing re­ally difficult

Martín SotoJul 25, 2022, 11:57 PM
13 points
2 comments2 min readLW link

[Question] How op­ti­mistic should we be about AI figur­ing out how to in­ter­pret it­self?

oh54321Jul 25, 2022, 10:09 PM
3 points
1 comment1 min readLW link

Pro­tec­tion­ism in One Coun­try: How In­dus­trial Policy Worked in Canada

Davis KedroskyJul 25, 2022, 10:08 PM
5 points
0 comments16 min readLW link
(daviskedrosky.substack.com)

Mis­takes as agency

pchvykovJul 25, 2022, 4:17 PM
12 points
8 comments4 min readLW link

My Bit­coin Th­e­sis @2022 - Part 1

aysajanJul 25, 2022, 3:49 PM
7 points
6 comments13 min readLW link

The Reader’s Guide to Op­ti­mal Mone­tary Policy

Ege ErdilJul 25, 2022, 3:10 PM
57 points
10 comments14 min readLW link

AGI Safety Needs Peo­ple With All Skil­lsets!

Severin T. SeehrichJul 25, 2022, 1:32 PM
28 points
0 comments2 min readLW link

[Question] Is there any ev­i­dence that hand­wash­ing does any­thing to pre­vent COVID?

mukashiJul 25, 2022, 7:34 AM
4 points
3 comments1 min readLW link

Open­ing Ses­sion Tips & Advice

CFAR!DuncanJul 25, 2022, 3:57 AM
96 points
3 comments14 min readLW link1 review

How much should we worry about mesa-op­ti­miza­tion challenges?

sudoJul 25, 2022, 3:56 AM
4 points
13 comments2 min readLW link