Linkpost: Choice Ex­plains Pos­i­tivity and Con­fir­ma­tion Bias

Gunnar_ZarnckeOct 1, 2020, 9:46 PM
8 points
0 comments1 min readLW link

Open & Wel­come Thread – Oc­to­ber 2020

Ben PaceOct 1, 2020, 7:06 PM
14 points
54 comments1 min readLW link

Hiring en­g­ineers and re­searchers to help al­ign GPT-3

paulfchristianoOct 1, 2020, 6:54 PM
206 points
13 comments3 min readLW link

Covid 10/​1: The Long Haul

ZviOct 1, 2020, 6:00 PM
95 points
22 comments9 min readLW link
(thezvi.wordpress.com)

Words and Implications

johnswentworthOct 1, 2020, 5:37 PM
62 points
25 comments8 min readLW link

Your Stan­dards are Too High

Neel NandaOct 1, 2020, 5:03 PM
26 points
2 comments14 min readLW link
(neelnanda.io)

Three car seats?

jefftkOct 1, 2020, 2:30 PM
18 points
9 comments1 min readLW link
(www.jefftk.com)

Fore­cast­ing Newslet­ter: Septem­ber 2020.

NunoSempereOct 1, 2020, 11:00 AM
21 points
3 comments11 min readLW link

[Question] Bab­ble challenge: 50 ways of send­ing some­thing to the moon

Bird ConceptOct 1, 2020, 4:20 AM
94 points
114 comments2 min readLW link1 review

AGI safety from first prin­ci­ples: Alignment

Richard_NgoOct 1, 2020, 3:13 AM
60 points
3 comments13 min readLW link

How to not be an alarmist

DirectedEvolutionSep 30, 2020, 9:35 PM
8 points
2 comments2 min readLW link

[Question] Com­pe­tence vs Alignment

kwiat.devSep 30, 2020, 9:03 PM
7 points
4 comments1 min readLW link

“Zero Sum” is a mis­nomer.

abramdemskiSep 30, 2020, 6:25 PM
120 points
34 comments6 min readLW link

Eval­u­at­ing Life Ex­ten­sion Ad­vo­cacy Foundation

emanuele ascaniSep 30, 2020, 6:04 PM
7 points
7 comments5 min readLW link

[AN #119]: AI safety when agents are shaped by en­vi­ron­ments, not rewards

Rohin ShahSep 30, 2020, 5:10 PM
11 points
0 comments11 min readLW link
(mailchi.mp)

Learn­ing how to learn

Neel NandaSep 30, 2020, 4:50 PM
44 points
0 comments15 min readLW link
(www.neelnanda.io)

In­dus­trial literacy

jasoncrawfordSep 30, 2020, 4:39 PM
308 points
130 comments3 min readLW link
(rootsofprogress.org)

Ja­son Crawford on the non-lin­ear model of in­no­va­tion: SSC On­line Meetup

JoshuaFoxSep 30, 2020, 10:13 AM
7 points
1 comment1 min readLW link

Holy Grails of Chemistry

chemslugSep 30, 2020, 2:03 AM
34 points
2 comments1 min readLW link

“Un­su­per­vised” trans­la­tion as an (in­tent) al­ign­ment problem

paulfchristianoSep 30, 2020, 12:50 AM
62 points
15 comments4 min readLW link
(ai-alignment.com)

[Question] Ex­am­ples of self-gov­er­nance to re­duce tech­nol­ogy risk?

JiaSep 29, 2020, 7:31 PM
10 points
4 comments1 min readLW link

AGI safety from first prin­ci­ples: Goals and Agency

Richard_NgoSep 29, 2020, 7:06 PM
77 points
15 comments15 min readLW link

Seek Up­side Risk

Neel NandaSep 29, 2020, 4:47 PM
20 points
6 comments9 min readLW link
(www.neelnanda.io)

Do­ing dis­course bet­ter: Stuff I wish I knew

dynomightSep 29, 2020, 2:34 PM
27 points
11 comments1 min readLW link
(dyno-might.github.io)

David Fried­man on Le­gal Sys­tems Very Differ­ent from Ours: SlateS­tarCodex On­line Meetup

JoshuaFoxSep 29, 2020, 11:18 AM
10 points
1 comment1 min readLW link

Read­ing Dis­cus­sion Group

NoSignalNoNoiseSep 29, 2020, 3:59 AM
6 points
0 comments1 min readLW link

Cambridge Vir­tual LW/​SSC Meetup

NoSignalNoNoiseSep 29, 2020, 3:42 AM
6 points
0 comments1 min readLW link

AGI safety from first prin­ci­ples: Superintelligence

Richard_NgoSep 28, 2020, 7:53 PM
87 points
8 comments9 min readLW link

AGI safety from first prin­ci­ples: Introduction

Richard_NgoSep 28, 2020, 7:53 PM
128 points
18 comments2 min readLW link1 review

[Question] is scope in­sen­si­tivity re­ally a brain er­ror?

Kaarlo TuomiSep 28, 2020, 6:37 PM
4 points
15 comments1 min readLW link

[Question] What De­ci­sion The­ory is Im­plied By Pre­dic­tive Pro­cess­ing?

johnswentworthSep 28, 2020, 5:20 PM
56 points
17 comments1 min readLW link

[Question] What are ex­am­ples of Ra­tion­al­ist fable-like sto­ries?

Mati_RoySep 28, 2020, 4:52 PM
19 points
42 comments1 min readLW link

Macro-Procrastination

Neel NandaSep 28, 2020, 4:07 PM
9 points
0 comments9 min readLW link
(www.neelnanda.io)

[Question] What are good ice breaker ques­tions for meet­ing peo­ple in this com­mu­nity?

Mati_RoySep 28, 2020, 3:07 PM
9 points
2 comments1 min readLW link

On De­stroy­ing the World

Chris_LeongSep 28, 2020, 7:38 AM
82 points
86 comments5 min readLW link

“Win First” vs “Chill First”

lionhearted (Sebastian Marshall)Sep 28, 2020, 6:48 AM
101 points
20 comments3 min readLW link

On “Not Screw­ing Up Ri­tual Can­dles”

RaemonSep 27, 2020, 9:55 PM
48 points
7 comments3 min readLW link

[Question] What to do with imi­ta­tion hu­mans, other than ask­ing them what the right thing to do is?

Charlie SteinerSep 27, 2020, 9:51 PM
10 points
6 comments1 min readLW link

[Question] What are good ra­tio­nal­ity ex­er­cises?

Ben PaceSep 27, 2020, 9:25 PM
54 points
25 comments1 min readLW link1 review

Puz­zle Games

Scott GarrabrantSep 27, 2020, 9:14 PM
57 points
70 comments7 min readLW link

[Question] What hard sci­ence fic­tion sto­ries also got the so­cial sci­ences right?

Mati_RoySep 27, 2020, 8:37 PM
15 points
30 comments1 min readLW link

Tips for the most im­mer­sive video calls

benkuhnSep 27, 2020, 8:36 PM
65 points
9 comments15 min readLW link
(www.benkuhn.net)

A long re­ply to Ben Garfinkel on Scru­ti­niz­ing Clas­sic AI Risk Arguments

Søren ElverlinSep 27, 2020, 5:51 PM
17 points
6 comments1 min readLW link

Not all com­mu­ni­ca­tion is ma­nipu­la­tion: Chap­er­ones don’t ma­nipu­late proteins

ChristianKlSep 27, 2020, 4:45 PM
35 points
14 comments2 min readLW link

Numer­acy ne­glect—A per­sonal postmortem

vlad.proexSep 27, 2020, 3:12 PM
81 points
29 comments9 min readLW link

San­der Ver­haegh on Quine’s Naturalism

Chris_LeongSep 27, 2020, 10:58 AM
8 points
0 comments1 min readLW link
(www.sanderverhaegh.nl)

The whirlpool of reality

Gordon Seidoh WorleySep 27, 2020, 2:36 AM
9 points
2 comments2 min readLW link

Blog posts as epistemic trust builders

Adam ZernerSep 27, 2020, 1:47 AM
18 points
7 comments2 min readLW link

Distributed pub­lic goods provision

paulfchristianoSep 26, 2020, 9:20 PM
27 points
3 comments5 min readLW link
(sideways-view.com)

Note­book for gen­er­at­ing fore­cast­ing bets

AmandangoSep 26, 2020, 8:36 PM
25 points
0 comments1 min readLW link