Gen­eral al­ign­ment properties

TurnTroutAug 8, 2022, 11:40 PM
51 points
2 comments1 min readLW link

Ex­per­i­ment: Be my math tu­tor?

sudoAug 8, 2022, 10:50 PM
12 points
5 comments1 min readLW link

En­cul­tured AI, Part 1 Ap­pendix: Rele­vant Re­search Examples

Aug 8, 2022, 10:44 PM
11 points
1 comment7 min readLW link

En­cul­tured AI Pre-plan­ning, Part 1: En­abling New Benchmarks

Aug 8, 2022, 10:44 PM
63 points
2 comments6 min readLW link

Broad Bas­ins and Data Compression

Aug 8, 2022, 8:33 PM
33 points
6 comments7 min readLW link

In­ter­pretabil­ity/​Tool-ness/​Align­ment/​Cor­rigi­bil­ity are not Composable

johnswentworthAug 8, 2022, 6:05 PM
143 points
13 comments3 min readLW link

LW Meetup @ DEFCON (Las Ve­gas) − 5-7pm Thu. Aug. 11 at Fo­rum Food Court (Cae­sars)

jchanAug 8, 2022, 2:57 PM
6 points
0 comments1 min readLW link

A suffi­ciently para­noid pa­per­clip maximizer

RomanSAug 8, 2022, 11:17 AM
18 points
10 comments2 min readLW link

[Question] In­stru­men­tal Goals and Many Gods Re­fu­ta­tion

aditya malikAug 8, 2022, 10:46 AM
−10 points
4 comments1 min readLW link

Area un­der the curve, Eat Dirt, Broc­coli Er­rors, Coper­ni­cus & Chaos

CFAR!DuncanAug 8, 2022, 8:17 AM
41 points
0 comments7 min readLW link

Steganog­ra­phy in Chain of Thought Reasoning

A RayAug 8, 2022, 3:47 AM
62 points
13 comments6 min readLW link

How Deadly Will Roughly-Hu­man-Level AGI Be?

David UdellAug 8, 2022, 1:59 AM
12 points
6 comments1 min readLW link

[Question] Can we get full au­dio for Eliezer’s con­ver­sa­tion with Sam Har­ris?

JakubKAug 7, 2022, 8:35 PM
30 points
8 comments1 min readLW link

Com­plex­ity No Bar to AI (Or, why Com­pu­ta­tional Com­plex­ity mat­ters less than you think for real life prob­lems)

Noosphere89Aug 7, 2022, 7:55 PM
17 points
14 comments3 min readLW link
(www.gwern.net)

The les­sons of Xanadu

jasoncrawfordAug 7, 2022, 5:59 PM
110 points
20 comments8 min readLW link
(jasoncrawford.org)

Care­ful with Caching

jefftkAug 7, 2022, 3:20 PM
15 points
3 comments1 min readLW link
(www.jefftk.com)

[Question] How would Log­i­cal De­ci­sion The­o­ries ad­dress the Psy­chopath But­ton?

Nathan1123Aug 7, 2022, 3:19 PM
5 points
33 comments1 min readLW link

Jack Clark on the re­al­ities of AI policy

Kaj_SotalaAug 7, 2022, 8:44 AM
68 points
3 comments3 min readLW link
(threadreaderapp.com)

Ex­pected (So­cial) Value

algrthmsAug 7, 2022, 8:16 AM
5 points
2 comments3 min readLW link

La­men­ta­tions, Gaza and Empathy

Yair HalberstadtAug 7, 2022, 7:55 AM
20 points
2 comments3 min readLW link

Paper read­ing as a Cargo Cult

jem-mosigAug 7, 2022, 7:50 AM
70 points
10 comments5 min readLW link

Most Ivy-smart stu­dents aren’t at Ivy-tier schools

Aaron BergmanAug 7, 2022, 3:18 AM
82 points
7 comments8 min readLW link
(www.aaronbergman.net)

Seat­tle Septem­ber meetup: Ab­sur­dity Bias

nsokolskyAug 7, 2022, 1:37 AM
3 points
0 comments1 min readLW link

Do meta-memes and meta-an­timemes ex­ist? e.g. ‘The map is not the ter­ri­tory’ is also a map

M. Y. ZuoAug 7, 2022, 1:17 AM
4 points
31 comments1 min readLW link

New­comb­ness of the Din­ing Philoso­phers Problem

Nathan1123Aug 6, 2022, 9:58 PM
10 points
2 comments2 min readLW link

[AMA] An­nounc­ing Open Phil’s Univer­sity Group Or­ga­nizer and Cen­tury Fel­low­ships [x-post]

Aug 6, 2022, 9:48 PM
14 points
0 comments13 min readLW link
(forum.effectivealtruism.org)

Bos­ton Rents Over Time II

jefftkAug 6, 2022, 9:20 PM
23 points
0 comments2 min readLW link
(www.jefftk.com)

Dwarves & D.Sci: Data Fortress

aphyerAug 6, 2022, 6:24 PM
38 points
26 comments3 min readLW link

A De­cep­tively Sim­ple Ar­gu­ment in fa­vor of Prob­lem Factorization

Logan ZoellnerAug 6, 2022, 5:32 PM
3 points
4 comments1 min readLW link

A Data limited future

Donald HobsonAug 6, 2022, 2:56 PM
52 points
25 comments2 min readLW link

Six weeks doesn’t make a habit

lynettebyeAug 6, 2022, 8:54 AM
48 points
1 comment3 min readLW link

Why I Am Skep­ti­cal of AI Reg­u­la­tion as an X-Risk Miti­ga­tion Strategy

A RayAug 6, 2022, 5:46 AM
31 points
14 comments2 min readLW link

My ad­vice on find­ing your own path

A RayAug 6, 2022, 4:57 AM
35 points
3 comments3 min readLW link

Pre­dic­tIt is clos­ing due to CFTC chang­ing its mind

eigenAug 6, 2022, 3:34 AM
20 points
4 comments1 min readLW link

Me­tac­u­lus and medians

rossryAug 6, 2022, 3:34 AM
18 points
4 comments4 min readLW link

An­nounc­ing the In­tro­duc­tion to ML Safety course

Aug 6, 2022, 2:46 AM
73 points
6 comments7 min readLW link

«Boundaries», Part 2: trends in EA’s han­dling of boundaries

Andrew_CritchAug 6, 2022, 12:42 AM
81 points
15 comments7 min readLW link

“Just hiring peo­ple” is some­times still ac­tu­ally possible

lcAug 5, 2022, 9:44 PM
38 points
11 comments5 min readLW link

The need for certainty

Thomas McMurtryAug 5, 2022, 8:18 PM
2 points
0 comments4 min readLW link

Rant on Prob­lem Fac­tor­iza­tion for Alignment

johnswentworthAug 5, 2022, 7:23 PM
102 points
53 comments6 min readLW link

Coun­ter­fac­tu­als are Con­fus­ing be­cause of an On­tolog­i­cal Shift

Chris_LeongAug 5, 2022, 7:03 PM
17 points
35 comments2 min readLW link

Orange county ACX/​Less-Wrong dis­cus­sion group and hang-out. (or­ange county)

Michael MichalchikAug 5, 2022, 6:25 PM
2 points
0 comments1 min readLW link

Gears-Level Un­der­stand­ing, De­liber­ate Perfor­mance, The Strate­gic Level

CFAR!DuncanAug 5, 2022, 5:11 PM
30 points
3 comments5 min readLW link

[Question] COVID-19 Group Test­ing Post-mortem?

gwernAug 5, 2022, 4:32 PM
72 points
6 comments2 min readLW link

Where are the red lines for AI?

Karl von WendtAug 5, 2022, 9:34 AM
26 points
10 comments6 min readLW link

Bridg­ing Ex­pected Utility Max­i­miza­tion and Optimization

Daniel HerrmannAug 5, 2022, 8:18 AM
25 points
5 comments14 min readLW link

Deon­tol­ogy and Tool AI

Nathan1123Aug 5, 2022, 5:20 AM
4 points
5 comments6 min readLW link

An at­tempt to un­der­stand the Com­plex­ity of Values

Dalton MaberyAug 5, 2022, 4:43 AM
3 points
0 comments5 min readLW link

$20K In Boun­ties for AI Safety Public Materials

Aug 5, 2022, 2:52 AM
71 points
9 comments6 min readLW link

Two Kids Crosswise

jefftkAug 5, 2022, 2:40 AM
16 points
3 comments1 min readLW link
(www.jefftk.com)