What does it mean to ap­ply de­ci­sion the­ory?

abramdemskiJul 8, 2020, 8:31 PM
54 points
6 comments8 min readLW link

The New Front­page De­sign & Open­ing Tag Creation!

habrykaJul 9, 2020, 4:37 AM
52 points
25 comments3 min readLW link

Al­gorith­mic In­tent: A Han­so­nian Gen­er­al­ized Anti-Zom­bie Principle

Zack_M_DavisJul 14, 2020, 6:03 AM
51 points
20 comments12 min readLW link

Up­date more slowly!

DavidmanheimJul 13, 2020, 7:10 AM
51 points
4 comments2 min readLW link

What should we do about net­work-effect mo­nop­o­lies?

benkuhnJul 6, 2020, 12:40 AM
51 points
17 comments1 min readLW link
(www.benkuhn.net)

Deal­ing with Cu­ri­os­ity-Stoppers

adamShimiJul 30, 2020, 10:05 PM
50 points
6 comments10 min readLW link

[Question] How should AI de­bate be judged?

abramdemskiJul 15, 2020, 10:20 PM
49 points
26 comments6 min readLW link

Site Redesign Feed­back Requested

RaemonJul 3, 2020, 10:28 PM
46 points
14 comments1 min readLW link

An­thro­po­mor­phiz­ing Humans

johnswentworthJul 17, 2020, 5:49 PM
46 points
6 comments2 min readLW link

[Question] What spe­cific dan­gers arise when ask­ing GPT-N to write an Align­ment Fo­rum post?

Matthew BarnettJul 28, 2020, 2:56 AM
45 points
14 comments1 min readLW link

Mesa-Op­ti­miz­ers vs “Steered Op­ti­miz­ers”

Steven ByrnesJul 10, 2020, 4:49 PM
45 points
7 comments8 min readLW link

Longevity in­ter­ven­tions when young

George3d6Jul 24, 2020, 11:25 AM
45 points
17 comments39 min readLW link
(cerebralab.com)

[Question] Why is pseudo-al­ign­ment “worse” than other ways ML can fail to gen­er­al­ize?

nostalgebraistJul 18, 2020, 10:54 PM
45 points
9 comments2 min readLW link

Del­e­gate a Forecast

AmandangoJul 28, 2020, 5:43 PM
44 points
25 comments2 min readLW link
(forum.effectivealtruism.org)

The “AI Dun­geons” Dragon Model is heav­ily path de­pen­dent (test­ing GPT-3 on ethics)

Rafael HarthJul 21, 2020, 12:14 PM
44 points
9 comments6 min readLW link

En­gag­ing Se­ri­ously with Short Timelines

sapphireJul 29, 2020, 7:21 PM
43 points
21 comments3 min readLW link

[Question] What prob­lem would you like to see Re­in­force­ment Learn­ing ap­plied to?

Julian SchrittwieserJul 8, 2020, 2:40 AM
43 points
4 comments1 min readLW link

Lurk­ing More Be­fore Join­ing Com­plex Conversations

RaemonJul 11, 2020, 5:11 PM
42 points
11 comments3 min readLW link

Writ­ing with GPT-3

Jacob FalkovichJul 24, 2020, 3:22 PM
42 points
0 comments4 min readLW link

[Question] What are the risks of per­ma­nent in­jury from COVID?

Daniel KokotajloJul 7, 2020, 4:30 PM
41 points
9 comments1 min readLW link

How to Find Sources in an Un­re­li­able World

ElizabethJul 1, 2020, 6:30 PM
41 points
8 comments2 min readLW link
(acesounderglass.com)

New Paper on Herd Im­mu­nity Thresholds

ZviJul 29, 2020, 8:50 PM
41 points
16 comments9 min readLW link
(thezvi.wordpress.com)

The Book of HPMOR Fanfics

Mati_RoyJul 3, 2020, 1:32 PM
41 points
18 comments1 min readLW link

En­vi­ron­ments as a bot­tle­neck in AGI development

Richard_NgoJul 17, 2020, 5:02 AM
41 points
19 comments6 min readLW link

Gen­er­al­iz­ing the Power-Seek­ing Theorems

TurnTroutJul 27, 2020, 12:28 AM
41 points
6 comments4 min readLW link

Ba­sic Con­ver­sa­tional Co­or­di­na­tion: Micro-co­or­di­na­tion of In­ten­tion

Eli TyreJul 27, 2020, 10:41 PM
41 points
7 comments2 min readLW link

Praise of some pop­u­lar LW articles

DirectedEvolutionJul 20, 2020, 12:32 AM
40 points
1 comment7 min readLW link

Align­ment pro­pos­als and com­plex­ity classes

evhubJul 16, 2020, 12:27 AM
40 points
26 comments13 min readLW link

Sur­vival in the im­moral maze of college

DirectedEvolutionJul 8, 2020, 9:27 PM
40 points
15 comments6 min readLW link

[Question] What if memes are com­mon in highly ca­pa­ble minds?

Daniel KokotajloJul 30, 2020, 8:45 PM
40 points
13 comments2 min readLW link

Covid 7/​30: Whack a Mole

ZviJul 30, 2020, 3:50 PM
39 points
4 comments10 min readLW link
(thezvi.wordpress.com)

Wiki-Tag FAQ

RubyJul 28, 2020, 9:57 PM
39 points
4 comments13 min readLW link

In praise of con­tribut­ing ex­am­ples, analo­gies and lingo

Adam ZernerJul 13, 2020, 6:43 AM
37 points
3 comments1 min readLW link

PSA: Cars don’t have ‘blindspots’

romeostevensitJul 1, 2020, 5:04 PM
37 points
5 comments1 min readLW link

Trade­off be­tween de­sir­able prop­er­ties for baseline choices in im­pact measures

VikaJul 4, 2020, 11:56 AM
37 points
24 comments5 min readLW link

“Should Black­mail Be Le­gal” Han­son/​Zvi De­bate (Sun July 26th, 3pm PDT)

Ben PaceJul 20, 2020, 4:06 AM
36 points
13 comments1 min readLW link

Pre­dic­tions for GPT-N

hippkeJul 29, 2020, 1:16 AM
36 points
31 comments1 min readLW link

Quan­tify­ing House­hold Trans­mis­sion of COVID-19

Owain_EvansJul 6, 2020, 11:19 AM
35 points
4 comments4 min readLW link

Evan Hub­inger on In­ner Align­ment, Outer Align­ment, and Pro­pos­als for Build­ing Safe Ad­vanced AI

Palus AstraJul 1, 2020, 5:30 PM
35 points
4 comments67 min readLW link

Was a ter­mi­nal de­gree nec­es­sary for in­vent­ing Boyle’s desider­ata?

DirectedEvolutionJul 10, 2020, 4:47 AM
35 points
18 comments5 min readLW link

Se­cond Wave Covid Deaths?

jefftkJul 1, 2020, 8:40 PM
35 points
16 comments2 min readLW link
(www.jefftk.com)

Clas­sifi­ca­tion of AI al­ign­ment re­search: de­con­fu­sion, “good enough” non-su­per­in­tel­li­gent AI al­ign­ment, su­per­in­tel­li­gent AI alignment

philip_bJul 14, 2020, 10:48 PM
35 points
25 comments3 min readLW link

Learn­ing the prior and generalization

evhubJul 29, 2020, 10:49 PM
34 points
16 comments4 min readLW link

How I use Google Forms in my Workflow

Harri BesceliJul 26, 2020, 12:17 PM
34 points
4 comments3 min readLW link

Book Re­view: Fooled by Randomness

SherrinfordJul 13, 2020, 9:02 PM
34 points
10 comments5 min readLW link

Cal­ibra­tion Prac­tice: Retro­d­ic­tions on Metaculus

RaemonJul 14, 2020, 6:35 PM
34 points
2 comments1 min readLW link

GPT-3 Gems

TurnTroutJul 23, 2020, 12:46 AM
33 points
10 comments48 min readLW link

School Has It Backwards

proshowersingerJul 12, 2020, 7:24 PM
33 points
10 comments2 min readLW link

Null-box­ing New­comb’s Problem

YitzJul 13, 2020, 4:32 PM
33 points
9 comments4 min readLW link

Covid-19: Anal­y­sis of Mor­tal­ity Data

ZviJul 11, 2020, 9:30 PM
32 points
12 comments12 min readLW link
(thezvi.wordpress.com)