A frame­work and open ques­tions for game the­o­retic shard modeling

Garrett BakerOct 21, 2022, 9:40 PM
11 points
4 comments4 min readLW link

Co­op­er­a­tors are more pow­er­ful than agents

Ivan VendrovOct 21, 2022, 8:02 PM
29 points
7 comments3 min readLW link

In­tel­li­gent be­havi­our across sys­tems, scales and substrates

Nora_AmmannOct 21, 2022, 5:09 PM
11 points
0 comments10 min readLW link

Deep­fake(?) Phishing

jefftkOct 21, 2022, 2:30 PM
37 points
9 comments1 min readLW link
(www.jefftk.com)

acronyms ftw

EmrikOct 21, 2022, 1:36 PM
−2 points
5 comments2 min readLW link

Cross­word puz­zle: LessWrong Hal­loween 2022

jchanOct 21, 2022, 12:41 PM
11 points
11 comments1 min readLW link

Weekly Roundup #2

ZviOct 21, 2022, 12:10 PM
37 points
2 comments11 min readLW link
(thezvi.wordpress.com)

Im­proved Se­cu­rity to Prevent Hacker-AI and Digi­tal Ghosts

Erland WittkotterOct 21, 2022, 10:11 AM
4 points
3 comments12 min readLW link

Two Guts

chanamessingerOct 21, 2022, 10:01 AM
21 points
0 comments1 min readLW link

The im­por­tance of study­ing sub­jec­tive experience

Q HomeOct 21, 2022, 8:43 AM
10 points
3 comments7 min readLW link

Le­gal Brief: Plu­ral­ity Vot­ing is Unconstitutional

c.troutOct 21, 2022, 4:55 AM
6 points
20 comments11 min readLW link
(medium.com)

Learn­ing so­cietal val­ues from law as part of an AGI al­ign­ment strategy

John NayOct 21, 2022, 2:03 AM
5 points
18 comments54 min readLW link

Covid 10/​20/​22: Wait, We Did WHAT?

ZviOct 20, 2022, 9:50 PM
55 points
16 comments16 min readLW link
(thezvi.wordpress.com)

When ap­par­ently pos­i­tive ev­i­dence can be nega­tive evidence

cataOct 20, 2022, 9:47 PM
19 points
5 comments1 min readLW link
(www.ncbi.nlm.nih.gov)

Plans Are Pre­dic­tions, Not Op­ti­miza­tion Targets

johnswentworthOct 20, 2022, 9:17 PM
108 points
20 comments4 min readLW link1 review

In­tro­duc­tion to ab­stract entropy

Alex_AltairOct 20, 2022, 9:03 PM
234 points
78 comments18 min readLW link1 review

Tra­jec­to­ries to 2036

ukc10014Oct 20, 2022, 8:23 PM
3 points
1 comment14 min readLW link

[Question] Rough Sketch for Product to En­hance Ci­ti­zen Par­ti­ci­pa­tion in Politics

Fer32dwt34r3dfszOct 20, 2022, 8:04 PM
13 points
5 comments1 min readLW link

The her­i­ta­bil­ity of hu­man val­ues: A be­hav­ior ge­netic cri­tique of Shard Theory

geoffreymillerOct 20, 2022, 3:51 PM
80 points
63 comments21 min readLW link

A Longter­mist case against Veganism

Connor TabarrokOct 20, 2022, 2:30 PM
−3 points
3 comments1 min readLW link

AI Re­search Pro­gram Pre­dic­tion Markets

tailcalledOct 20, 2022, 1:42 PM
38 points
10 comments1 min readLW link

[Question] Is the mean­ing of words cho­sen/​in­ter­preted to max­i­mize cor­re­la­tions with other rele­vant queries?

tailcalledOct 20, 2022, 10:03 AM
9 points
9 comments1 min readLW link

How to Write Read­able Posts

David HartsoughOct 20, 2022, 7:48 AM
7 points
0 comments1 min readLW link

Notes on “Can you con­trol the past”

So8resOct 20, 2022, 3:41 AM
64 points
41 comments21 min readLW link

Rhyth­mic Baby Toys

jefftkOct 20, 2022, 1:50 AM
15 points
1 comment1 min readLW link
(www.jefftk.com)

[Question] What Does AI Align­ment Suc­cess Look Like?

ShmiOct 20, 2022, 12:32 AM
23 points
7 comments1 min readLW link

Scal­ing Laws for Re­ward Model Overoptimization

Oct 20, 2022, 12:20 AM
103 points
13 comments1 min readLW link
(arxiv.org)

What is Con­scious­ness?

belkarxOct 19, 2022, 9:14 PM
3 points
2 comments2 min readLW link

What to do if a nu­clear weapon is used in Ukraine?

Valentin2026Oct 19, 2022, 6:43 PM
13 points
9 comments3 min readLW link

[Question] If I asked for an ex­pla­na­tion of a perfect Utopia, could you give one?

AkkiraOct 19, 2022, 5:56 PM
−4 points
2 comments1 min readLW link

[Question] Should we push for re­quiring AI train­ing data to be li­censed?

ChristianKlOct 19, 2022, 5:49 PM
37 points
32 comments1 min readLW link

Hacker-AI and Digi­tal Ghosts – Pre-AGI

Erland WittkotterOct 19, 2022, 3:33 PM
9 points
7 comments8 min readLW link

The re­ward func­tion is already how well you ma­nipu­late humans

KerryOct 19, 2022, 1:52 AM
20 points
9 comments2 min readLW link

Re­sponse to Katja Grace’s AI x-risk counterarguments

Oct 19, 2022, 1:17 AM
77 points
18 comments15 min readLW link

(OLD) An Ex­tremely Opinionated An­no­tated List of My Favourite Mechanis­tic In­ter­pretabil­ity Papers

Neel NandaOct 18, 2022, 9:08 PM
72 points
5 comments12 min readLW link
(www.neelnanda.io)

Distil­led Rep­re­sen­ta­tions Re­search Agenda

Oct 18, 2022, 8:59 PM
15 points
2 comments8 min readLW link

Draft­ing a Covid Survey

jefftkOct 18, 2022, 7:30 PM
15 points
2 comments2 min readLW link
(www.jefftk.com)

How To Make Pre­dic­tion Mar­kets Use­ful For Align­ment Work

johnswentworthOct 18, 2022, 7:01 PM
97 points
18 comments2 min readLW link

A con­ver­sa­tion about Katja’s coun­ter­ar­gu­ments to AI risk

Oct 18, 2022, 6:40 PM
43 points
9 comments33 min readLW link

ACX Zurich Oc­to­ber Meetup

MBOct 18, 2022, 6:24 PM
1 point
1 comment1 min readLW link

Un­tapped Po­ten­tial at 13-18

belkarxOct 18, 2022, 6:09 PM
82 points
53 comments1 min readLW link

[Question] How easy is it to su­per­vise pro­cesses vs out­comes?

Noosphere89Oct 18, 2022, 5:48 PM
3 points
0 comments1 min readLW link

Is GitHub Copi­lot in le­gal trou­ble?

tcelferactOct 18, 2022, 4:19 PM
35 points
2 comments1 min readLW link

Me­tac­u­lus is build­ing a team ded­i­cated to AI forecasting

ChristianWilliamsOct 18, 2022, 4:08 PM
3 points
0 comments1 min readLW link

How to Take Over the Uni­verse (in Three Easy Steps)

WriterOct 18, 2022, 3:04 PM
47 points
17 comments12 min readLW link
(youtu.be)

Science of Deep Learn­ing—a tech­ni­cal agenda

Marius HobbhahnOct 18, 2022, 2:54 PM
36 points
7 comments4 min readLW link

My search for a re­li­able breakfast

tomdekanOct 18, 2022, 9:42 AM
6 points
17 comments3 min readLW link
(www.tomdekan.com)

In­finite Pos­si­bil­ity Space and the Shut­down Problem

magfrumpOct 18, 2022, 5:37 AM
9 points
0 comments2 min readLW link
(www.magfrump.net)

Au­di­tion to perform in Bay Sec­u­lar Solstice

mingyuanOct 18, 2022, 3:10 AM
25 points
3 comments1 min readLW link

De­ci­sion the­ory does not im­ply that we get to have nice things

So8resOct 18, 2022, 3:04 AM
171 points
73 comments26 min readLW link2 reviews