China Covid Up­date #1

ZviApr 11, 2022, 1:40 PM
88 points
22 comments3 min readLW link
(thezvi.wordpress.com)

The case for turn­ing glowfic into Sequences

Thomas KwaApr 27, 2022, 6:58 AM
87 points
29 comments5 min readLW link

Ineffec­tive Altruism

lsusrApr 23, 2022, 10:07 PM
86 points
17 comments1 min readLW link

PaLM in “Ex­trap­o­lat­ing GPT-N perfor­mance”

Lukas FinnvedenApr 6, 2022, 1:05 PM
85 points
19 comments2 min readLW link

Us­ing pre­dic­tion mar­kets to gen­er­ate LessWrong posts

Matthew BarnettApr 1, 2022, 4:33 PM
85 points
11 comments1 min readLW link

Fore­cast­ing Newslet­ter: April 2222

NunoSempereApr 1, 2022, 7:07 AM
83 points
7 comments6 min readLW link

Org an­nounce­ment: [AC]RC

Vivek HebbarApr 17, 2022, 5:24 PM
82 points
11 comments1 min readLW link

My Recol­lec­tion of How This All Got Started

Gordon Seidoh WorleyApr 6, 2022, 3:22 AM
82 points
12 comments4 min readLW link

Fi­nally En­ter­ing Alignment

Ulisse MiniApr 10, 2022, 5:01 PM
81 points
8 comments2 min readLW link

Re­port like­li­hood ratios

Ege ErdilApr 23, 2022, 5:10 PM
80 points
9 comments7 min readLW link

Early 2022 Paper Round-up

jsteinhardtApr 14, 2022, 8:50 PM
80 points
4 comments3 min readLW link
(bounded-regret.ghost.io)

Repli­cat­ing and ex­tend­ing the grabby aliens model

Tristan CookApr 23, 2022, 12:38 AM
80 points
20 comments51 min readLW link

What I Was Think­ing About Be­fore Alignment

johnswentworthApr 6, 2022, 4:08 PM
78 points
8 comments5 min readLW link

Use­ful Vices for Wicked Problems

HoldenKarnofskyApr 12, 2022, 7:30 PM
78 points
2 comments17 min readLW link1 review
(www.cold-takes.com)

Why pes­simism sounds smart

jasoncrawfordApr 25, 2022, 8:10 PM
76 points
15 comments1 min readLW link
(rootsofprogress.org)

Make a Movie Show­ing Align­ment Failures

Logan RiggsApr 13, 2022, 9:54 PM
75 points
11 comments2 min readLW link

[$20K in Prizes] AI Safety Ar­gu­ments Competition

Apr 26, 2022, 4:13 PM
75 points
518 comments3 min readLW link

Pro­ject In­tro: Selec­tion The­o­rems for Modularity

Apr 4, 2022, 12:59 PM
74 points
20 comments16 min readLW link

[Question] Best non-text­books on ev­ery subject

Yair HalberstadtApr 4, 2022, 11:54 AM
74 points
23 comments1 min readLW link

Kids Posts Retrospective

jefftkApr 1, 2022, 2:10 PM
73 points
1 comment7 min readLW link
(www.jefftk.com)

[In­tro to brain-like-AGI safety] 13. Sym­bol ground­ing & hu­man so­cial instincts

Steven ByrnesApr 27, 2022, 1:30 PM
73 points
15 comments15 min readLW link

[Question] Good Heart Dona­tion Lottery

Gordon Seidoh WorleyApr 1, 2022, 5:51 PM
72 points
14 comments2 min readLW link

Elicit: Lan­guage Models as Re­search Assistants

Apr 9, 2022, 2:56 PM
71 points
6 comments13 min readLW link

Jaan Tal­linn’s 2021 Philan­thropy Overview

jaanApr 28, 2022, 9:55 AM
71 points
2 comments1 min readLW link
(jaan.online)

[Closed] Hiring a math­e­mat­i­cian to work on the learn­ing-the­o­retic AI al­ign­ment agenda

Vanessa KosoyApr 19, 2022, 6:44 AM
69 points
21 comments2 min readLW link

An­nounc­ing Im­pact Is­land: A New EA Real­ity TV Show

LinchApr 1, 2022, 5:28 PM
69 points
14 comments4 min readLW link
(forum.effectivealtruism.org)

Op­ti­miz­ing crop plant­ing with mixed in­te­ger lin­ear pro­gram­ming in Stardew Valley

hapaninApr 5, 2022, 6:42 PM
68 points
4 comments7 min readLW link

SERI ML Align­ment The­ory Schol­ars Pro­gram 2022

Apr 27, 2022, 12:43 AM
67 points
6 comments3 min readLW link

How dath ilan co­or­di­nates around solv­ing alignment

Thomas KwaApr 13, 2022, 4:22 AM
65 points
46 comments5 min readLW link

Be­com­ing a Staff Engineer

Gordon Seidoh WorleyApr 3, 2022, 2:30 AM
64 points
33 comments6 min readLW link

Prize for Align­ment Re­search Tasks

Apr 29, 2022, 8:57 AM
64 points
38 comments10 min readLW link

A method of writ­ing con­tent eas­ily with lit­tle anxiety

jessicataApr 8, 2022, 10:11 PM
64 points
19 comments3 min readLW link
(unstableontology.com)

China Covid #2

ZviApr 22, 2022, 7:00 PM
64 points
9 comments8 min readLW link
(thezvi.wordpress.com)

[Question] Con­vince me that hu­man­ity *isn’t* doomed by AGI

YitzApr 15, 2022, 5:26 PM
61 points
50 comments1 min readLW link

In­creas­ing De­mand­ing­ness in EA

jefftkApr 29, 2022, 1:20 AM
61 points
22 comments3 min readLW link
(www.jefftk.com)

Ukraine Post #8: Risk of Nu­clear War

ZviApr 4, 2022, 12:00 PM
60 points
17 comments13 min readLW link
(thezvi.wordpress.com)

What Is a Ma­jor Chord?

jefftkApr 24, 2022, 7:20 AM
59 points
11 comments3 min readLW link
(www.jefftk.com)

Epistemic Slipperiness

RaemonApr 11, 2022, 1:48 AM
59 points
18 comments7 min readLW link

Com­mon Knowl­edge is a Cir­cle Game for Toddlers

ryan_bApr 13, 2022, 3:24 PM
58 points
1 comment1 min readLW link

Not-Use­less Ad­vice For Deal­ing With Things You Don’t Want to Do

Rafael HarthApr 4, 2022, 4:37 PM
58 points
11 comments6 min readLW link

All I Know is that I Know Nothing

lsusrApr 22, 2022, 3:33 PM
57 points
13 comments2 min readLW link

Un­con­trol­lable Su­per-Pow­er­ful Explosives

Sammy MartinApr 2, 2022, 8:13 PM
55 points
17 comments5 min readLW link

Good Heart Week Is Over!

Ben PaceApr 8, 2022, 6:43 AM
55 points
35 comments1 min readLW link

Save Hu­man­ity! Breed Sapi­ent Oc­to­puses!

Yair HalberstadtApr 5, 2022, 6:39 PM
55 points
17 comments1 min readLW link

The Cage of the Language

Martin SustrikApr 13, 2022, 5:20 AM
54 points
19 comments2 min readLW link

Kosher Hot Dogs

johnswentworthApr 1, 2022, 3:10 PM
54 points
8 comments3 min readLW link

Two Proso­cial Re­jec­tion Norms

EmrikApr 28, 2022, 8:53 PM
54 points
21 comments3 min readLW link

Con­vinc­ing Peo­ple of Align­ment with Street Epistemology

Logan RiggsApr 12, 2022, 11:43 PM
54 points
4 comments3 min readLW link

The in­ter­net makes it eas­ier to co­op­er­ate, that’s the problem

David Hugh-JonesApr 19, 2022, 3:25 PM
54 points
9 comments4 min readLW link
(wyclif.substack.com)

Reflec­tions on My Own Miss­ing Mood

Lone PineApr 21, 2022, 4:19 PM
53 points
25 comments5 min readLW link