All200520062007200820092010201120122013201420152016201720182019202020212022202320242025
AllJanFebMarAprMayJunJulAugSepOctNovDec
All12345678910111213141516171819202122232425262728293031

Benign model-free RL

paulfchristianoDec 2, 2018, 4:10 AM
15 points
1 comment7 min readLW link

Any­one use the “read time” on Post Items?

RaemonDec 1, 2018, 11:16 PM
19 points
11 comments1 min readLW link

Novem­ber 2018 gw­ern.net newsletter

gwernDec 1, 2018, 1:57 PM
35 points
0 commentsLW link
(www.gwern.net)

In­tu­itions about goal-di­rected behavior

Rohin ShahDec 1, 2018, 4:25 AM
54 points
15 comments6 min readLW link

Tak­ing vi­tamin D3 with K2 in the morning

ChristianKlNov 30, 2018, 7:00 PM
54 points
47 comments4 min readLW link

Over­con­fi­dent talk­ing down, hum­ble or hos­tile talk­ing up

ozziegooenNov 30, 2018, 12:41 PM
49 points
19 comments3 min readLW link

Ten­ta­tively con­sid­er­ing emo­tional sto­ries (IFS and “get­ting into Self”)

Kaj_SotalaNov 30, 2018, 7:40 AM
40 points
31 comments4 min readLW link
(kajsotala.fi)

Iter­ated Distil­la­tion and Amplification

Ajeya CotraNov 30, 2018, 4:47 AM
47 points
14 comments6 min readLW link

Mov­ing Factward

Tyrrell_McAllisterNov 29, 2018, 5:54 AM
14 points
11 comments1 min readLW link

For­mal Open Prob­lem in De­ci­sion Theory

Scott GarrabrantNov 29, 2018, 3:25 AM
37 points
28 comments4 min readLW link

Reflec­tive or­a­cles as a solu­tion to the con­verse Law­vere problem

SamEisenstatNov 29, 2018, 3:23 AM
35 points
2 comments7 min readLW link

The Ubiquitous Con­verse Law­vere Problem

Scott GarrabrantNov 29, 2018, 3:16 AM
23 points
0 comments2 min readLW link

Hyper­real Brouwer

Scott GarrabrantNov 29, 2018, 3:15 AM
31 points
2 comments6 min readLW link

Madi­son Sols­tice Gathering

mingyuanNov 28, 2018, 9:36 PM
16 points
0 comments1 min readLW link

Coun­ter­in­tu­itive Com­par­a­tive Advantage

Wei DaiNov 28, 2018, 8:33 PM
85 points
8 comments2 min readLW link

Sta­bi­lize-Reflect-Execute

ozziegooenNov 28, 2018, 5:26 PM
30 points
1 comment2 min readLW link

Ge­net­i­cally Mod­ified Hu­mans Born (Allegedly)

ryan_bNov 28, 2018, 4:14 PM
29 points
12 comments1 min readLW link

Or­a­cle In­duc­tion Proofs

DiffractorNov 28, 2018, 8:12 AM
5 points
0 comments9 min readLW link

Bounded Or­a­cle Induction

DiffractorNov 28, 2018, 8:11 AM
25 points
0 comments9 min readLW link

Dou­ble-Dip­ping in Dun­ning—Kruger

isovectorNov 28, 2018, 3:40 AM
88 points
32 comments3 min readLW link

Win­ter Sols­tice 2018 Roundup

RaemonNov 28, 2018, 3:09 AM
50 points
8 comments1 min readLW link

Corrigibility

paulfchristianoNov 27, 2018, 9:50 PM
57 points
8 comments6 min readLW link

SSC Meetup Moscow #2

nikkouNov 27, 2018, 6:21 PM
1 point
0 comments1 min readLW link

Sum­mary: Sur­real Decisions

Chris_LeongNov 27, 2018, 2:15 PM
29 points
20 comments3 min readLW link

CFAR re­union Europe

Jan_KulveitNov 27, 2018, 12:02 PM
10 points
0 comments3 min readLW link

How democ­racy ends: a re­view and reevaluation

Richard_NgoNov 27, 2018, 10:50 AM
15 points
7 comments6 min readLW link
(thinkingcomplete.blogspot.com)

MIRI’s 2018 Fundraiser

MaloNov 27, 2018, 5:30 AM
60 points
1 comment7 min readLW link

Is Science Slow­ing Down?

Scott AlexanderNov 27, 2018, 3:30 AM
131 points
77 comments9 min readLW link1 review
(slatestarcodex.com)

Bodega Bay: workshop

KatjaGraceNov 27, 2018, 3:20 AM
38 points
1 comment2 min readLW link
(worldlypositions.tumblr.com)

Align­ment Newslet­ter #34

Rohin ShahNov 26, 2018, 11:10 PM
24 points
0 comments10 min readLW link
(mailchi.mp)

Boltz­mann Brains, Si­mu­la­tions and self re­fut­ing hy­poth­e­sis

Donald HobsonNov 26, 2018, 7:09 PM
1 point
9 comments1 min readLW link

Quan­tum Me­chan­ics, Noth­ing to do with Consciousness

Donald HobsonNov 26, 2018, 6:59 PM
5 points
27 comments3 min readLW link

Sta­tus model

BuckyNov 26, 2018, 3:05 PM
26 points
7 comments3 min readLW link

Hu­mans Con­sult­ing HCH

paulfchristianoNov 25, 2018, 11:18 PM
39 points
9 comments1 min readLW link

Ap­proval-di­rected bootstrapping

paulfchristianoNov 25, 2018, 11:18 PM
24 points
0 comments1 min readLW link

How rapidly are GPUs im­prov­ing in price perfor­mance?

gallabytesNov 25, 2018, 7:54 PM
31 points
9 commentsLW link
(mediangroup.org)

Values Weren’t Com­plex, Once.

DavidmanheimNov 25, 2018, 9:17 AM
36 points
13 comments2 min readLW link

A cul­ture of ex­ploita­tion?

Bae's TheoremNov 24, 2018, 10:00 PM
1 point
3 comments1 min readLW link

Fixed Point Discussion

Scott GarrabrantNov 24, 2018, 8:53 PM
45 points
2 comments4 min readLW link

Four fac­tors that mod­er­ate the in­ten­sity of emotions

RubyNov 24, 2018, 8:40 PM
63 points
11 comments8 min readLW link

deluks917 on On­line Weirdos

Jacob FalkovichNov 24, 2018, 5:03 PM
24 points
3 comments10 min readLW link

[Mon­treal] Towards High-As­surance Ad­vanced AI Sys­tems by Richard Mallah

Mati_RoyNov 24, 2018, 6:24 AM
3 points
0 comments1 min readLW link

Up­com­ing: Open Questions

RaemonNov 24, 2018, 1:39 AM
41 points
7 comments2 min readLW link

A Dragon Con­fronts the Terasem Movement

AlephywrNov 24, 2018, 1:31 AM
−4 points
10 comments25 min readLW link
(dancefighterredux.wordpress.com)

What if peo­ple sim­ply fore­casted your fu­ture choices?

ozziegooenNov 23, 2018, 10:52 AM
16 points
6 comments6 min readLW link

Over­sight of Un­safe Sys­tems via Dy­namic Safety En­velopes

DavidmanheimNov 23, 2018, 8:37 AM
10 points
2 comments2 min readLW link

On MIRI’s new re­search directions

Rob BensingerNov 22, 2018, 11:42 PM
53 points
12 comments1 min readLW link
(intelligence.org)

LW Up­date 2018-11-22 – Abridged Comments

RaemonNov 22, 2018, 10:11 PM
11 points
16 comments1 min readLW link

Ap­proval-di­rected agents

paulfchristianoNov 22, 2018, 9:15 PM
31 points
10 comments15 min readLW link

Believ­ing oth­ers’ priors

rkNov 22, 2018, 8:44 PM
8 points
19 comments7 min readLW link