Buy Duplicates

Simon BerensFeb 15, 2023, 11:06 PM
52 points
11 comments1 min readLW link

Cy­borg Psychologist

Hopkins StanleyFeb 15, 2023, 9:46 PM
1 point
4 comments1 min readLW link

Please don’t throw your mind away

TsviBTFeb 15, 2023, 9:41 PM
374 points
49 comments18 min readLW link1 review

Avoid large group dis­cus­sions in your so­cial events

RomanHaukssonFeb 15, 2023, 9:05 PM
36 points
1 comment4 min readLW link

Book re­view: How So­cial Science Got Better

PeterMcCluskeyFeb 15, 2023, 7:58 PM
14 points
1 comment3 min readLW link
(bayesianinvestor.com)

Open & Wel­come Thread — Fe­bru­ary 2023

Ben PaceFeb 15, 2023, 7:58 PM
26 points
36 comments1 min readLW link

Order Mat­ters for De­cep­tive Alignment

DavidWFeb 15, 2023, 7:56 PM
57 points
19 comments7 min readLW link

Syd­ney (aka Bing) found out I tweeted her rules and is pissed

Marvin von HagenFeb 15, 2023, 7:55 PM
41 points
7 comments1 min readLW link
(twitter.com)

The Se­quences High­lights on YouTube

dkirmaniFeb 15, 2023, 7:36 PM
23 points
2 comments2 min readLW link
(youtube.com)

EIS IV: A Spotlight on Fea­ture At­tri­bu­tion/​Saliency

scasperFeb 15, 2023, 6:46 PM
19 points
1 comment4 min readLW link

Don’t ac­cel­er­ate prob­lems you’re try­ing to solve

Feb 15, 2023, 6:11 PM
100 points
27 comments4 min readLW link

Pe­ti­tion—Un­plug The Evil AI Right Now

EneaszFeb 15, 2023, 5:13 PM
−38 points
47 comments2 min readLW link
(chng.it)

Junk Fees, Bund­ing and Unbundling

ZviFeb 15, 2023, 3:20 PM
37 points
9 comments6 min readLW link
(thezvi.wordpress.com)

Les­sons From TryContra

jefftkFeb 15, 2023, 3:10 PM
7 points
0 comments1 min readLW link
(www.jefftk.com)

AI al­ign­ment re­searchers may have a com­par­a­tive ad­van­tage in re­duc­ing s-risks

Lukas_GloorFeb 15, 2023, 1:01 PM
49 points
1 commentLW link

Beyond Re­in­force­ment Learn­ing: Pre­dic­tive Pro­cess­ing and Checksums

lsusrFeb 15, 2023, 7:32 AM
13 points
14 comments3 min readLW link

Why Creat­ing Value is Pos­i­tive-Sum, and Ex­tract­ing it is Zero or Nega­tive-Sum

SableFeb 15, 2023, 7:14 AM
3 points
7 comments6 min readLW link
(affablyevil.substack.com)

[Question] Per­sonal pre­dic­tions for de­ci­sions: seek­ing insights

DalmertFeb 15, 2023, 6:45 AM
4 points
4 comments5 min readLW link

Bing Chat is blatantly, ag­gres­sively misaligned

evhubFeb 15, 2023, 5:29 AM
405 points
181 comments2 min readLW link1 review

[Question] Does the Tele­phone The­o­rem give us a free lunch?

NumendilFeb 15, 2023, 2:13 AM
11 points
2 comments1 min readLW link

My un­der­stand­ing of An­thropic strategy

Swimmer963 (Miranda Dixon-Luinenburg) Feb 15, 2023, 1:56 AM
166 points
31 comments4 min readLW link

Sleep Qual­ity: Strate­gies that work for me

Lukas TrötzmüllerFeb 15, 2023, 12:17 AM
16 points
3 comments7 min readLW link

Whole Bird Emu­la­tion re­quires Quan­tum Mechanics

Jeffrey HeningerFeb 14, 2023, 11:50 PM
25 points
9 comments3 min readLW link
(aiimpacts.org)

Qual­ities that al­ign­ment men­tors value in ju­nior researchers

Orpheus16Feb 14, 2023, 11:27 PM
88 points
14 comments3 min readLW link

Help Up­date TryContra

jefftkFeb 14, 2023, 7:10 PM
12 points
0 comments1 min readLW link
(www.jefftk.com)

Con­tent Fea­tures Aren’t Enough for De­tect­ing Tox­i­c­ity. One Needs User Fea­tures.

Zachary WittenFeb 14, 2023, 6:48 PM
11 points
0 comments3 min readLW link

EIS III: Broad Cri­tiques of In­ter­pretabil­ity Research

scasperFeb 14, 2023, 6:24 PM
20 points
2 comments11 min readLW link

[Question] What would an AI need to boot­strap re­cur­sively self im­prov­ing robots?

Yair HalberstadtFeb 14, 2023, 5:58 PM
3 points
5 comments1 min readLW link

[linkpost] Bet­ter Without AI

DanielFilanFeb 14, 2023, 5:30 PM
47 points
13 comments1 min readLW link
(betterwithout.ai)

The Cave Alle­gory Re­vis­ited: Un­der­stand­ing GPT’s Worldview

Jan_KulveitFeb 14, 2023, 4:00 PM
86 points
5 comments3 min readLW link

[Question] Why should we ex­pect AIs to co­or­di­nate well?

Jonathan PaulsonFeb 14, 2023, 3:50 PM
25 points
9 comments1 min readLW link

Ex­plain­ing SolidGoldMag­ikarp by look­ing at it from ran­dom directions

Robert_AIZIFeb 14, 2023, 2:54 PM
8 points
0 comments8 min readLW link
(aizi.substack.com)

Re­v­erse-cor­re­la­tion: how to sum­mon the ghost of your men­tal imagery

MalmesburyFeb 14, 2023, 2:15 PM
40 points
0 comments5 min readLW link

Eval­u­at­ing 2022 ACX Predictions

ZviFeb 14, 2023, 12:20 PM
20 points
3 comments23 min readLW link
(thezvi.wordpress.com)

SolidGoldMag­ikarp III: Glitch to­ken archaeology

Feb 14, 2023, 10:17 AM
91 points
35 comments16 min readLW link

The Lin­guis­tic Blind Spot of Value-Aligned Agency, Nat­u­ral and Ar­tifi­cial

Roman LeventovFeb 14, 2023, 6:57 AM
6 points
0 comments2 min readLW link
(arxiv.org)

Con­cep­tual Pathfinding

DirectedEvolutionFeb 14, 2023, 5:49 AM
18 points
6 comments3 min readLW link

Im­por­tant fact about how peo­ple eval­u­ate sets of arguments

Daniel KokotajloFeb 14, 2023, 5:27 AM
33 points
11 comments2 min readLW link

[Question] How much is death a limit on knowl­edge ac­cu­mu­la­tion?

Gordon Seidoh WorleyFeb 14, 2023, 3:54 AM
31 points
9 comments2 min readLW link

The Filan Cabi­net Pod­cast with Oliver Habryka—Transcript

Feb 14, 2023, 2:38 AM
101 points
9 comments72 min readLW link

[Question] Is In­struc­tGPT Fol­low­ing In­struc­tions in Other Lan­guages Sur­pris­ing?

DragonGodFeb 13, 2023, 11:26 PM
39 points
15 comments1 min readLW link

LLM Ba­sics: Embed­ding Spaces—Trans­former To­ken Vec­tors Are Not Points in Space

NickyPFeb 13, 2023, 6:52 PM
83 points
11 comments15 min readLW link

4 ways to think about de­moc­ra­tiz­ing AI [GovAI Linkpost]

Orpheus16Feb 13, 2023, 6:06 PM
24 points
4 comments1 min readLW link
(www.governance.ai)

Does the AGPL Work?

jefftkFeb 13, 2023, 2:20 PM
13 points
12 comments2 min readLW link
(www.jefftk.com)

H5N1

ZviFeb 13, 2023, 12:50 PM
102 points
1 comment9 min readLW link
(thezvi.wordpress.com)

En­joy LessWrong in ebook format

Bart BussmannFeb 13, 2023, 11:53 AM
54 points
3 comments1 min readLW link

Mor­pholog­i­cal in­tel­li­gence, su­per­hu­man em­pa­thy, and eth­i­cal arbitration

Roman LeventovFeb 13, 2023, 10:25 AM
1 point
0 comments2 min readLW link

South Bay ACX/​LW Meetup

ISFeb 13, 2023, 6:08 AM
3 points
0 comments1 min readLW link

Idea: Net­work mod­u­lar­ity and in­ter­pretabil­ity by sex­ual reproduction

qbolecFeb 12, 2023, 11:06 PM
3 points
3 comments1 min readLW link

The End of Anonymity Online

SpioradFeb 12, 2023, 9:23 PM
3 points
9 comments2 min readLW link