What DALL-E 2 can and can­not do

Swimmer963 (Miranda Dixon-Luinenburg) May 1, 2022, 11:51 PM
353 points
303 comments9 min readLW link

Be­ware boast­ing about non-ex­is­tent fore­cast­ing track records

Jotto999May 20, 2022, 7:20 PM
338 points
112 comments5 min readLW link1 review

Six Di­men­sions of Oper­a­tional Ad­e­quacy in AGI Projects

Eliezer YudkowskyMay 30, 2022, 5:00 PM
310 points
66 comments13 min readLW link1 review

Is AI Progress Im­pos­si­ble To Pre­dict?

alyssavanceMay 15, 2022, 6:30 PM
277 points
39 comments2 min readLW link

Pro­jec­tLawful.com: Eliezer’s lat­est story, past 1M words

Eliezer YudkowskyMay 11, 2022, 6:18 AM
234 points
112 comments1 min readLW link4 reviews

Visi­ble Home­less­ness in SF: A Quick Break­down of Causes

alyssavanceMay 25, 2022, 1:40 AM
209 points
32 comments2 min readLW link

Benign Boundary Violations

Duncan Sabien (Deactivated)May 26, 2022, 6:48 AM
207 points
84 comments18 min readLW link1 review

On sav­ing one’s world

Rob BensingerMay 17, 2022, 7:53 PM
192 points
4 comments1 min readLW link

De­liber­ate Grieving

RaemonMay 30, 2022, 8:49 PM
187 points
16 comments9 min readLW link2 reviews

Tran­scripts of in­ter­views with AI researchers

Vael GatesMay 9, 2022, 5:57 AM
170 points
9 comments2 min readLW link

Deep­mind’s Gato: Gen­er­al­ist Agent

Daniel KokotajloMay 12, 2022, 4:01 PM
165 points
62 comments1 min readLW link

A Bird’s Eye View of the ML Field [Prag­matic AI Safety #2]

May 9, 2022, 5:18 PM
163 points
8 comments35 min readLW link

Re­peal the For­eign Dredge Act of 1906

ZviMay 5, 2022, 3:20 PM
159 points
16 comments19 min readLW link
(thezvi.wordpress.com)

Deep­Mind is hiring for the Scal­able Align­ment and Align­ment Teams

May 13, 2022, 12:17 PM
150 points
34 comments9 min readLW link

Re­shap­ing the AI Industry

Thane RuthenisMay 29, 2022, 10:54 PM
147 points
35 comments21 min readLW link

High-stakes al­ign­ment via ad­ver­sar­ial train­ing [Red­wood Re­search re­port]

May 5, 2022, 12:59 AM
142 points
29 comments9 min readLW link

LessWrong Now Has Dark Mode

jimrandomhMay 10, 2022, 1:21 AM
135 points
31 comments1 min readLW link

The case for be­com­ing a black-box in­ves­ti­ga­tor of lan­guage models

BuckMay 6, 2022, 2:35 PM
126 points
20 comments3 min readLW link

We have achieved Noob Gains in AI

phdeadMay 18, 2022, 8:56 PM
118 points
20 comments7 min readLW link

Nar­ra­tive Syncing

AnnaSalamonMay 1, 2022, 1:48 AM
118 points
48 comments7 min readLW link1 review

Pop­u­lar ed­u­ca­tion in Swe­den: much more than you wanted to know

Henrik KarlssonMay 17, 2022, 8:07 PM
118 points
3 comments11 min readLW link
(escapingflatland.substack.com)

RL with KL penalties is bet­ter seen as Bayesian inference

May 25, 2022, 9:23 AM
114 points
17 comments12 min readLW link

[In­tro to brain-like-AGI safety] 15. Con­clu­sion: Open prob­lems, how to help, AMA

Steven ByrnesMay 17, 2022, 3:11 PM
97 points
10 comments15 min readLW link

[Question] What is Go­ing On With CFAR?

niplavMay 28, 2022, 3:21 PM
95 points
34 comments1 min readLW link

I only be­lieve in the paranormal

MalmesburyMay 24, 2022, 12:15 PM
94 points
8 comments2 min readLW link

Op­ti­miza­tion at a Distance

johnswentworthMay 16, 2022, 5:58 PM
88 points
16 comments4 min readLW link

For­mula for Dy­ing Babies

ZviMay 17, 2022, 4:50 PM
88 points
12 comments6 min readLW link
(thezvi.wordpress.com)

Ceiling Air Purifier

jefftkMay 30, 2022, 7:20 PM
87 points
11 comments2 min readLW link
(www.jefftk.com)

PSA: The Se­quences don’t need to be read in sequence

kaveMay 23, 2022, 2:53 AM
87 points
7 comments1 min readLW link

Gato as the Dawn of Early AGI

David UdellMay 15, 2022, 6:52 AM
85 points
29 comments12 min readLW link

Var­i­ous Align­ment Strate­gies (and how likely they are to work)

Logan ZoellnerMay 3, 2022, 4:54 PM
84 points
34 comments11 min readLW link

In­tro­duc­tion to Prag­matic AI Safety [Prag­matic AI Safety #1]

May 9, 2022, 5:06 PM
80 points
3 comments6 min readLW link

“A Gen­er­al­ist Agent”: New Deep­Mind Publication

1a3ornMay 12, 2022, 3:30 PM
79 points
43 comments1 min readLW link

How to be skep­ti­cal about med­i­ta­tion/​Buddhism

ViliamMay 1, 2022, 10:30 AM
78 points
47 comments2 min readLW link

In­for­ma­tion se­cu­rity con­sid­er­a­tions for AI and the long term future

May 2, 2022, 8:54 PM
76 points
6 comments10 min readLW link

“Tech com­pany sin­gu­lar­i­ties”, and steer­ing them to re­duce x-risk

Andrew_CritchMay 13, 2022, 5:24 PM
75 points
11 comments4 min readLW link

In­tro­duc­ing the ML Safety Schol­ars Program

May 4, 2022, 4:01 PM
74 points
3 comments3 min readLW link

The “Mea­sur­ing Stick of Utility” Problem

johnswentworthMay 25, 2022, 4:17 PM
74 points
25 comments3 min readLW link

New Water Qual­ity x Obe­sity Dataset Available

ElizabethMay 27, 2022, 7:50 PM
74 points
14 comments2 min readLW link
(acesounderglass.com)

Why I Define My Ex­pe­rience At the Monas­tic Academy As Sex­ual Assault

HS2021May 24, 2022, 8:17 AM
72 points
24 comments15 min readLW link

Con­di­tions for math­e­mat­i­cal equiv­alence of Stochas­tic Gra­di­ent Des­cent and Nat­u­ral Selection

Oliver SourbutMay 9, 2022, 9:38 PM
70 points
19 comments8 min readLW link1 review
(www.oliversourbut.net)

Glass Puppet

lsusrMay 25, 2022, 11:01 PM
70 points
8 comments3 min readLW link

Get­ting GPT-3 to pre­dict Me­tac­u­lus questions

MathiasKBMay 6, 2022, 6:01 AM
69 points
9 comments2 min readLW link

Ap­ply to the sec­ond iter­a­tion of the ML for Align­ment Boot­camp (MLAB 2) in Berkeley [Aug 15 - Fri Sept 2]

BuckMay 6, 2022, 4:23 AM
69 points
0 comments6 min readLW link

au­ton­omy: the miss­ing AGI in­gre­di­ent?

nostalgebraistMay 25, 2022, 12:33 AM
69 points
12 comments6 min readLW link

Distributed Decisions

johnswentworthMay 29, 2022, 2:43 AM
66 points
6 comments6 min readLW link

14 Tech­niques to Ac­cel­er­ate Your Learning

May 19, 2022, 1:59 PM
66 points
10 comments11 min readLW link

What We Owe the Past

Austin ChenMay 5, 2022, 11:46 AM
66 points
38 comments5 min readLW link

Ethan Ca­ballero on Pri­vate Scal­ing Progress

Michaël TrazziMay 5, 2022, 6:32 PM
63 points
2 comments2 min readLW link
(theinsideview.github.io)

The Last Paperclip

Logan ZoellnerMay 12, 2022, 7:25 PM
63 points
15 comments18 min readLW link