AI Align­ment Writ­ing Day Roundup #2

Ben PaceOct 7, 2019, 11:36 PM
33 points
2 comments3 min readLW link

Bets and updating

Eigil RischelOct 7, 2019, 11:06 PM
32 points
5 comments2 min readLW link

Oc­cam’s Ra­zor May Be Suffi­cient to In­fer the Prefer­ences of Ir­ra­tional Agents: A re­ply to Arm­strong & Mindermann

Daniel KokotajloOct 7, 2019, 7:52 PM
47 points
39 comments7 min readLW link

The sen­tence struc­ture of mathematics

countedblessingsOct 7, 2019, 6:58 PM
41 points
15 comments2 min readLW link

[Link] Book Re­view: ‘The AI Does Not Hate You’ by Tom Chivers (Scott Aaron­son)

eigenOct 7, 2019, 6:16 PM
19 points
0 comments1 min readLW link

[AN #67]: Creat­ing en­vi­ron­ments in which to study in­ner al­ign­ment failures

Rohin ShahOct 7, 2019, 5:10 PM
17 points
0 comments8 min readLW link
(mailchi.mp)

The Gears of Impact

TurnTroutOct 7, 2019, 2:44 PM
54 points
16 comments1 min readLW link

Hy­brid Lot­tery Admission

jefftkOct 7, 2019, 1:20 PM
10 points
0 comments1 min readLW link
(www.jefftk.com)

Re­place judges with Key­ne­sian beauty con­tests?

John_MaxwellOct 7, 2019, 4:00 AM
30 points
5 comments3 min readLW link

[Question] What do the baby eaters tell us about ethics?

spookyuserOct 6, 2019, 10:27 PM
7 points
36 comments1 min readLW link

In­tro­duc­tion to In­tro­duc­tion to Cat­e­gory Theory

countedblessingsOct 6, 2019, 2:43 PM
114 points
19 comments2 min readLW link

What is cat­e­gory the­ory?

countedblessingsOct 6, 2019, 2:33 PM
65 points
6 comments3 min readLW link

Ad­vanced Dances

jefftkOct 6, 2019, 11:10 AM
10 points
0 comments1 min readLW link
(www.jefftk.com)

Mako’s Notes from Skep­toid’s 13 Hour 13th Birth­day Stream

mako yassOct 6, 2019, 9:43 AM
6 points
0 comments3 min readLW link

[Event] Meet­ing in Myrhorod, Novem­ber 16

Mary ChernyshenkoOct 6, 2019, 8:45 AM
3 points
0 comments1 min readLW link

Who lacks the qualia of con­scious­ness?

Richard_KennawayOct 5, 2019, 7:49 PM
29 points
55 comments1 min readLW link

Eight O’Clock is Relative

jefftkOct 5, 2019, 4:20 PM
13 points
1 comment2 min readLW link
(www.jefftk.com)

[Question] How do I view my replies?

DocumentOct 5, 2019, 4:05 PM
7 points
2 comments1 min readLW link

[Question] What em­piri­cal work has been done that bears on the ‘freebit pic­ture’ of free will?

DanielFilanOct 4, 2019, 11:11 PM
9 points
5 comments1 min readLW link

Ideal Num­ber of Parents

jefftkOct 4, 2019, 8:00 PM
20 points
4 comments3 min readLW link
(www.jefftk.com)

13 Causes of Bad Science (Novum Or­ganum Book 1: 69-92)

Francis BaconOct 4, 2019, 7:52 PM
33 points
1 comment30 min readLW link

[Question] What are your strate­gies for avoid­ing micro-mis­takes?

NaiveTortoiseOct 4, 2019, 6:42 PM
17 points
13 comments1 min readLW link

Septem­ber 2019 gw­ern.net newsletter

gwernOct 4, 2019, 4:44 PM
21 points
0 commentsLW link
(www.gwern.net)

The AI is the model

Charlie SteinerOct 4, 2019, 8:11 AM
14 points
1 comment3 min readLW link

Con­scious Pro­pri­o­cep­tion.

leggiOct 4, 2019, 4:33 AM
20 points
8 comments7 min readLW link

De­bate on In­stru­men­tal Con­ver­gence be­tween LeCun, Rus­sell, Ben­gio, Zador, and More

Ben PaceOct 4, 2019, 4:08 AM
221 points
61 comments15 min readLW link2 reviews

AI Align­ment Open Thread Oc­to­ber 2019

habrykaOct 4, 2019, 1:28 AM
26 points
58 comments1 min readLW link

[Link] Tools for thought (Ma­tuschak & Niel­sen)

ioannesOct 4, 2019, 12:42 AM
21 points
7 comments2 min readLW link

Long-Term Fu­ture Fund: Au­gust 2019 grant recommendations

habrykaOct 3, 2019, 8:41 PM
35 points
0 comments64 min readLW link
(forum.effectivealtruism.org)

New Petrov Game Brainstorm

AlexeiOct 3, 2019, 7:48 PM
17 points
4 comments2 min readLW link

To Be De­cided #1

Ian David MossOct 3, 2019, 7:30 PM
8 points
2 comments3 min readLW link

DC LW: Priors

rusalkiiOct 3, 2019, 6:11 PM
2 points
0 comments1 min readLW link

Solv­ing the for­get­ting. Spaced rep­e­ti­tion be­yond ra­tio­nal­ity com­mu­nity.

MrAKaDeusOct 3, 2019, 3:03 PM
4 points
0 comments1 min readLW link
(medium.com)

Can we make peace with moral in­de­ter­mi­nacy?

Charlie SteinerOct 3, 2019, 12:56 PM
16 points
8 comments4 min readLW link

Com­ments are back!

jefftkOct 3, 2019, 10:50 AM
7 points
0 comments1 min readLW link
(www.jefftk.com)

Late to the Party: Climate

ThewalOct 3, 2019, 1:36 AM
1 point
0 comments1 min readLW link

[Link] (EA Pod­cast) Global Op­ti­mum: How to Learn Better

Daniel_GambacortaOct 3, 2019, 12:29 AM
4 points
0 comments1 min readLW link

[Link] What do con­ser­va­tives know that liber­als don’t (and vice versa)?

defilippisOct 2, 2019, 4:14 PM
15 points
6 comments1 min readLW link

What are we as­sum­ing about util­ity func­tions?

Grue_SlinkyOct 2, 2019, 3:11 PM
17 points
24 comments2 min readLW link

Hu­man in­stincts, sym­bol ground­ing, and the blank-slate neocortex

Steven ByrnesOct 2, 2019, 12:06 PM
62 points
24 comments11 min readLW link

Toy model #6: Ra­tion­al­ity and par­tial preferences

Stuart_ArmstrongOct 2, 2019, 12:04 PM
11 points
0 comments2 min readLW link

Dou­ble Tongue Whistling

jefftkOct 2, 2019, 11:10 AM
8 points
1 comment1 min readLW link
(www.jefftk.com)

Cam­bridge LW/​SSC Meetup

NoSignalNoNoiseOct 2, 2019, 3:37 AM
6 points
0 comments1 min readLW link

Does the US nu­clear policy still tar­get cities?

Jeffrey LadishOct 2, 2019, 12:18 AM
61 points
7 comments10 min readLW link

Sur­vival and Flour­ish­ing Fund Ap­pli­ca­tions clos­ing in 3 days

habrykaOct 2, 2019, 12:12 AM
19 points
0 comments1 min readLW link

Open & Wel­come Thread—Oc­to­ber 2019

RubyOct 1, 2019, 11:10 PM
10 points
46 comments1 min readLW link

LW Team Up­dates—Oc­to­ber 2019

RubyOct 1, 2019, 11:08 PM
30 points
10 comments3 min readLW link

World State is the Wrong Ab­strac­tion for Impact

TurnTroutOct 1, 2019, 9:03 PM
67 points
19 comments2 min readLW link

Med­i­ta­tions on Moloch and Pair Debugging

Dan ValentineOct 1, 2019, 7:37 PM
1 point
0 comments1 min readLW link

[Question] What fund­ing sources ex­ist for tech­ni­cal AI safety re­search?

johnswentworthOct 1, 2019, 3:30 PM
27 points
5 comments1 min readLW link