We learn long-last­ing strate­gies to pro­tect our­selves from dan­ger and rejection

Richard_NgoMay 16, 2023, 4:36 PM
86 points
5 comments5 min readLW link

How I ap­ply (so-called) Non-Violent Communication

Kaj_SotalaMay 15, 2023, 9:56 AM
86 points
28 comments3 min readLW link

Some Thoughts on Virtue Ethics for AIs

peligrietzerMay 2, 2023, 5:46 AM
83 points
8 comments4 min readLW link

Wikipe­dia as an in­tro­duc­tion to the al­ign­ment problem

SoerenMindMay 29, 2023, 6:43 PM
83 points
10 comments1 min readLW link
(en.wikipedia.org)

Mob and Bailey

ScrewtapeMay 25, 2023, 10:14 PM
82 points
17 comments7 min readLW link1 review

Hell is Game The­ory Folk Theorems

jessicataMay 1, 2023, 3:16 AM
81 points
102 comments5 min readLW link1 review
(unstableontology.com)

How I learned to stop wor­ry­ing and love skill trees

junk heap homotopyMay 23, 2023, 4:08 AM
81 points
3 comments1 min readLW link

Les­sons learned from offer­ing in-office nu­tri­tional testing

ElizabethMay 15, 2023, 11:20 PM
80 points
11 comments14 min readLW link
(acesounderglass.com)

AI #10: Code In­ter­preter and Ge­off Hinton

ZviMay 4, 2023, 2:00 PM
80 points
7 comments78 min readLW link
(thezvi.wordpress.com)

Re­sult Of The Bounty/​Con­test To Ex­plain In­fra-Bayes In The Lan­guage Of Game Theory

johnswentworthMay 9, 2023, 4:35 PM
79 points
0 comments1 min readLW link

Bet­ter debates

TsviBTMay 10, 2023, 7:34 PM
78 points
7 comments3 min readLW link

Brief notes on the Se­nate hear­ing on AI oversight

DizietMay 16, 2023, 10:29 PM
77 points
2 comments2 min readLW link

Resi­d­ual stream norms grow ex­po­nen­tially over the for­ward pass

May 7, 2023, 12:46 AM
77 points
24 comments11 min readLW link

AI #12:The Quest for Sane Regulations

ZviMay 18, 2023, 1:20 PM
77 points
12 comments64 min readLW link
(thezvi.wordpress.com)

What 2025 looks like

RubyMay 1, 2023, 10:53 PM
75 points
17 comments15 min readLW link

Self-lead­er­ship and self-love dis­solve anger and trauma

Richard_NgoMay 22, 2023, 10:30 PM
73 points
7 comments5 min readLW link

Re­solv­ing in­ter­nal con­flicts re­quires listen­ing to what parts want

Richard_NgoMay 19, 2023, 12:04 AM
71 points
0 comments4 min readLW link

Solv­ing the Mechanis­tic In­ter­pretabil­ity challenges: EIS VII Challenge 2

May 25, 2023, 3:37 PM
71 points
1 comment13 min readLW link

Nat­u­ral­ist Collection

LoganStrohlMay 6, 2023, 12:37 AM
71 points
7 comments15 min readLW link

Helping your Se­na­tor Pre­pare for the Up­com­ing Sam Alt­man Hearing

Tiago de VassalMay 14, 2023, 10:45 PM
69 points
2 comments1 min readLW link
(aisafetytour.com)

Seek­ing (Paid) Case Stud­ies on Standards

HoldenKarnofskyMay 26, 2023, 5:58 PM
69 points
9 comments11 min readLW link

Orthog­o­nal’s For­mal-Goal Align­ment the­ory of change

Tamsin LeakeMay 5, 2023, 10:36 PM
69 points
13 comments4 min readLW link
(carado.moe)

The Light­cone The­o­rem: A Bet­ter Foun­da­tion For Nat­u­ral Ab­strac­tion?

johnswentworthMay 15, 2023, 2:24 AM
69 points
25 comments6 min readLW link

Long Covid Risks: 2023 Update

ElizabethMay 6, 2023, 6:20 PM
69 points
11 comments4 min readLW link
(acesounderglass.com)

Ad­vice for in­ter­act­ing with busy people

Severin T. SeehrichMay 4, 2023, 1:31 PM
68 points
4 comments4 min readLW link

Turn­ing off lights with model editing

Sam MarksMay 12, 2023, 8:25 PM
68 points
5 comments2 min readLW link
(arxiv.org)

AI #11: In Search of a Moat

ZviMay 11, 2023, 3:40 PM
67 points
28 comments81 min readLW link
(thezvi.wordpress.com)

Avoid­ing xrisk from AI doesn’t mean fo­cus­ing on AI xrisk

Stuart_ArmstrongMay 2, 2023, 7:27 PM
67 points
7 comments3 min readLW link

[Linkpost] “Gover­nance of su­per­in­tel­li­gence” by OpenAI

Daniel_EthMay 22, 2023, 8:15 PM
67 points
20 commentsLW link

Some quotes from Tues­day’s Se­nate hear­ing on AI

Daniel_EthMay 17, 2023, 12:13 PM
66 points
9 commentsLW link

An Im­pos­si­bil­ity Proof Rele­vant to the Shut­down Prob­lem and Corrigibility

AudereMay 2, 2023, 6:52 AM
66 points
13 comments9 min readLW link

The Com­pleat Cybornaut

May 19, 2023, 8:44 AM
66 points
2 comments16 min readLW link

TinyS­to­ries: Small Lan­guage Models That Still Speak Co­her­ent English

Ulisse MiniMay 28, 2023, 10:23 PM
66 points
8 comments2 min readLW link
(arxiv.org)

What does it take to ban a thing?

qbolecMay 8, 2023, 11:00 AM
66 points
18 comments5 min readLW link

‘Fun­da­men­tal’ vs ‘ap­plied’ mechanis­tic in­ter­pretabil­ity research

Lee SharkeyMay 23, 2023, 6:26 PM
65 points
6 comments3 min readLW link

Get­ting Your Eyes On

LoganStrohlMay 2, 2023, 12:33 AM
65 points
11 comments14 min readLW link

[New] Re­jected Con­tent Section

May 4, 2023, 1:43 AM
65 points
21 comments5 min readLW link

An­nounc­ing “Key Phenom­ena in AI Risk” (fa­cil­i­tated read­ing group)

May 9, 2023, 12:31 AM
65 points
4 comments2 min readLW link

Idea: med­i­cal hy­pothe­ses app for mys­te­ri­ous chronic illnesses

riceissaMay 19, 2023, 8:49 PM
64 points
8 comments3 min readLW link

Jaan Tal­linn’s 2022 Philan­thropy Overview

jaanMay 14, 2023, 3:35 PM
64 points
2 comments1 min readLW link
(jaan.online)

How MATS ad­dresses “mass move­ment build­ing” concerns

Ryan KiddMay 4, 2023, 12:55 AM
63 points
9 comments3 min readLW link

Sys­tems that can­not be un­safe can­not be safe

DavidmanheimMay 2, 2023, 8:53 AM
62 points
27 comments2 min readLW link

Nat­u­ral­ist Experimentation

LoganStrohlMay 10, 2023, 4:28 AM
62 points
14 comments10 min readLW link

Some Sum­maries of Agent Foun­da­tions Work

mattmacdermottMay 15, 2023, 4:09 PM
62 points
1 comment13 min readLW link

Google “We Have No Moat, And Nei­ther Does OpenAI”

Chris_LeongMay 4, 2023, 6:23 PM
61 points
28 comments1 min readLW link
(www.semianalysis.com)

Re­ply to a fer­til­ity doc­tor con­cern­ing poly­genic em­bryo screening

GeneSmithMay 29, 2023, 9:50 PM
59 points
6 comments8 min readLW link

A tech­ni­cal note on bil­in­ear lay­ers for interpretability

Lee SharkeyMay 8, 2023, 6:06 AM
59 points
0 comments1 min readLW link
(arxiv.org)

The Office of Science and Tech­nol­ogy Policy put out a re­quest for in­for­ma­tion on A.I.

HiroSakurabaMay 24, 2023, 1:33 PM
59 points
4 comments1 min readLW link
(www.whitehouse.gov)

Col­lec­tive Identity

May 18, 2023, 9:00 AM
59 points
12 comments8 min readLW link

Be­fore smart AI, there will be many mediocre or spe­cial­ized AIs

Lukas FinnvedenMay 26, 2023, 1:38 AM
58 points
14 comments9 min readLW link1 review