Oper­a­tional­iz­ing New­comb’s Problem

ErickBallNov 11, 2019, 10:52 PM
34 points
23 comments1 min readLW link

Ul­tra-sim­plified re­search agenda

Stuart_ArmstrongNov 22, 2019, 2:29 PM
34 points
4 comments1 min readLW link

Prac­ti­cal Guidelines for Me­mory Reconsolidation

Matt GoldenbergNov 13, 2019, 7:54 PM
34 points
5 comments2 min readLW link

Meetup Notes: Ole Peters on ergodicity

OrbordeNov 3, 2019, 11:31 PM
32 points
13 comments4 min readLW link

[Question] Hard to find fac­tors mess­ing up ex­per­i­ments: Ex­am­ples?

HazardNov 15, 2019, 5:46 PM
32 points
13 comments1 min readLW link

SSC Mee­tups Every­where Retrospective

Scott AlexanderNov 28, 2019, 7:10 PM
32 points
0 comments7 min readLW link
(slatestarcodex.com)

Robin Han­son on the fu­tur­ist fo­cus on AI

abergalNov 13, 2019, 9:50 PM
31 points
24 comments1 min readLW link
(aiimpacts.org)

[Per­sonal Ex­per­i­ment] Coun­ter­bal­anc­ing Risk-Aversion

lsusrNov 15, 2019, 8:34 AM
31 points
6 comments1 min readLW link

Ex­plain­ing why false ideas spread is more fun than why true ones do

Matthew BarnettNov 24, 2019, 8:21 PM
31 points
6 comments1 min readLW link

Com­ment, Don’t Message

jefftkNov 18, 2019, 4:00 PM
30 points
5 comments2 min readLW link
(www.jefftk.com)

EA Fo­rum AMA—MIRI’s Buck Shlegeris

Rob BensingerNov 15, 2019, 11:27 PM
30 points
0 comments2 min readLW link
(forum.effectivealtruism.org)

Ex­per­i­ments and Consent

jefftkNov 10, 2019, 2:50 PM
30 points
45 comments1 min readLW link
(www.jefftk.com)

Neu­ral nets as a model for how hu­mans make and un­der­stand vi­sual art

Owain_EvansNov 9, 2019, 4:53 PM
28 points
7 comments2 min readLW link
(owainevans.github.io)

LW Team Up­dates—Novem­ber 2019 (Sub­scrip­tions & More)

RubyNov 8, 2019, 2:39 AM
28 points
4 comments2 min readLW link

More vari­a­tions on pseudo-alignment

evhubNov 4, 2019, 11:24 PM
27 points
8 comments2 min readLW link

Effect of Advertising

jefftkNov 26, 2019, 2:30 PM
26 points
24 comments2 min readLW link
(www.jefftk.com)

[AN #72]: Align­ment, ro­bust­ness, method­ol­ogy, and sys­tem build­ing as re­search pri­ori­ties for AI safety

Rohin ShahNov 6, 2019, 6:10 PM
26 points
4 comments10 min readLW link
(mailchi.mp)

[Question] Do you get value out of con­tentless com­ments?

DanielFilanNov 21, 2019, 9:57 PM
26 points
21 comments1 min readLW link

What makes a good life? This is my map.

MartinBNov 22, 2019, 3:10 PM
26 points
20 comments4 min readLW link

Thoughts on im­ple­ment­ing cor­rigible ro­bust alignment

Steven ByrnesNov 26, 2019, 2:06 PM
26 points
2 comments6 min readLW link

A Brief In­tro to Do­main Theory

DiffractorNov 21, 2019, 3:24 AM
26 points
4 comments14 min readLW link

Thoughts on Robin Han­son’s AI Im­pacts interview

Steven ByrnesNov 24, 2019, 1:40 AM
25 points
3 comments7 min readLW link

Defin­ing AI wireheading

Stuart_ArmstrongNov 21, 2019, 1:04 PM
25 points
9 comments4 min readLW link

Break­ing Or­a­cles: su­per­ra­tional­ity and acausal trade

Stuart_ArmstrongNov 25, 2019, 10:40 AM
25 points
15 comments1 min readLW link

Junto: Ques­tions for Mee­tups and Rando Convos

SebastianG Nov 20, 2019, 10:11 PM
23 points
1 comment1 min readLW link

Goal-think­ing vs de­sire-thinking

SniffnoyNov 10, 2019, 12:31 AM
23 points
11 comments4 min readLW link

Im­pos­si­ble moral prob­lems and moral authority

Charlie SteinerNov 18, 2019, 9:28 AM
22 points
8 comments3 min readLW link

Epistemic Spot Check: Un­con­di­tional Parenting

ElizabethNov 10, 2019, 8:10 PM
22 points
6 comments3 min readLW link
(acesounderglass.com)

A test for sym­bol ground­ing meth­ods: true zero-sum games

Stuart_ArmstrongNov 26, 2019, 2:15 PM
22 points
2 comments2 min readLW link

Analysing: Danger­ous mes­sages from fu­ture UFAI via Oracles

Stuart_ArmstrongNov 22, 2019, 2:17 PM
22 points
16 comments4 min readLW link

Lite Blocking

jefftkNov 5, 2019, 1:50 PM
21 points
4 comments2 min readLW link
(www.jefftk.com)

Cur­tis Yarvin on A The­ory of Per­va­sive Error

Zack_M_DavisNov 26, 2019, 7:27 AM
21 points
6 comments1 min readLW link
(americanmind.org)

Per­sonal qual­ity experimentation

KatjaGraceNov 6, 2019, 9:50 PM
21 points
1 comment1 min readLW link
(meteuphoric.com)

Pla­tonic re­wards, re­ward fea­tures, and re­wards as information

Stuart_ArmstrongNov 12, 2019, 7:38 PM
20 points
2 comments7 min readLW link

So­lar One Year In

jefftkNov 22, 2019, 3:20 PM
20 points
2 comments1 min readLW link
(www.jefftk.com)

[AN #74]: Separat­ing benefi­cial AI into com­pe­tence, al­ign­ment, and cop­ing with impacts

Rohin ShahNov 20, 2019, 6:20 PM
19 points
0 comments7 min readLW link
(mailchi.mp)

Doxa, Episteme, and Gno­sis Revisited

Gordon Seidoh WorleyNov 20, 2019, 7:35 PM
19 points
2 comments9 min readLW link

Judg­ment, Pu­n­ish­ment, and the In­for­ma­tion-Sup­pres­sion Field

BenquoNov 6, 2019, 5:44 PM
19 points
12 comments3 min readLW link
(benjaminrosshoffman.com)

Pric­ing ex­ter­nal­ities is not nec­es­sar­ily eco­nom­i­cally efficient

OrbordeNov 9, 2019, 12:07 PM
19 points
9 comments1 min readLW link
(www.daviddfriedman.com)

Poli­tics is work and work needs breaks

KatjaGraceNov 4, 2019, 5:10 PM
19 points
0 comments2 min readLW link
(meteuphoric.com)

Cat­a­lyst: a col­lab­o­ra­tive biose­cu­rity summit

epiphiNov 8, 2019, 9:37 PM
18 points
0 comments1 min readLW link

Ar­gu­ing about housing

jefftkNov 14, 2019, 5:00 PM
18 points
13 comments2 min readLW link
(www.jefftk.com)

Draw­ing on Walls

jefftkNov 19, 2019, 3:00 PM
17 points
1 comment1 min readLW link
(www.jefftk.com)

Book Re­view: Man’s Search for Mean­ing by Vic­tor Frankel

Chris_LeongNov 4, 2019, 11:21 AM
17 points
0 comments4 min readLW link

[Question] Liter­a­ture on memet­ics?

moridinamaelNov 7, 2019, 7:18 PM
17 points
2 comments1 min readLW link

Shared Cache is Go­ing Away

jefftkNov 1, 2019, 3:10 PM
17 points
6 comments1 min readLW link
(www.jefftk.com)

[Question] Is daily caf­feine con­sump­tion benefi­cial to pro­duc­tivity?

ChristianKlNov 26, 2019, 1:13 PM
17 points
19 comments1 min readLW link

Hard Prob­lems in Cryp­tocur­rency: Five Years Later—Buterin

philip_bNov 24, 2019, 9:38 AM
17 points
0 comments1 min readLW link
(vitalik.ca)

A Prac­ti­cal The­ory of Me­mory Reconsolidation

Matt GoldenbergNov 13, 2019, 7:52 PM
16 points
16 comments2 min readLW link

The Value Defi­ni­tion Problem

Sammy MartinNov 18, 2019, 7:56 PM
15 points
6 comments11 min readLW link