Ra­tion­al­ist Seder: A Story of War

Raemon3 Jun 2017 20:17 UTC
12 points
14 comments2 min readLW link

Co­op­er­a­tive Or­a­cles: Non­ex­ploited Bargaining

Scott Garrabrant3 Jun 2017 0:39 UTC
6 points
6 comments3 min readLW link

Co­op­er­a­tive Or­a­cles: Strat­ified Pareto Op­tima and Al­most Strat­ified Pareto Optima

Scott Garrabrant3 Jun 2017 0:38 UTC
5 points
8 comments4 min readLW link

Co­op­er­a­tive Or­a­cles: Introduction

Scott Garrabrant3 Jun 2017 0:36 UTC
12 points
3 comments2 min readLW link

En­tan­gled Equil­ibria and the Twin Pri­son­ers’ Dilemma

Scott Garrabrant2 Jun 2017 22:09 UTC
5 points
2 comments3 min readLW link

An al­gorithm with prefer­ences: from zero to one variable

Stuart_Armstrong2 Jun 2017 16:35 UTC
4 points
0 comments1 min readLW link

Re­ward/​value learn­ing for re­in­force­ment learning

Stuart_Armstrong2 Jun 2017 16:34 UTC
0 points
2 comments2 min readLW link

The best value in­differ­ence method (so far)

Stuart_Armstrong2 Jun 2017 16:33 UTC
0 points
9 comments5 min readLW link

How to judge moral learn­ing failure

Stuart_Armstrong2 Jun 2017 16:32 UTC
0 points
2 comments2 min readLW link

Coun­ter­fac­tu­als on POMDP

Stuart_Armstrong2 Jun 2017 16:30 UTC
2 points
0 comments2 min readLW link

Un­in­fluence­able learn­ing agents

Stuart_Armstrong2 Jun 2017 16:30 UTC
3 points
7 comments1 min readLW link

On­tol­ogy, lost pur­poses, and in­stru­men­tal goals

Stuart_Armstrong2 Jun 2017 16:28 UTC
0 points
1 comment1 min readLW link

Cor­rigi­bil­ity thoughts I: car­ing about mul­ti­ple things

Stuart_Armstrong2 Jun 2017 16:27 UTC
2 points
0 comments3 min readLW link

Cor­rigi­bil­ity thoughts II: the robot operator

Stuart_Armstrong2 Jun 2017 16:27 UTC
0 points
12 comments2 min readLW link

Cor­rigi­bil­ity thoughts III: ma­nipu­lat­ing ver­sus deceiving

Stuart_Armstrong2 Jun 2017 16:27 UTC
0 points
0 comments1 min readLW link

The ra­dioac­tive bur­rito and learn­ing from pos­i­tive examples

Stuart_Armstrong2 Jun 2017 16:25 UTC
0 points
2 comments1 min readLW link

Thoughts on Quantilizers

Stuart_Armstrong2 Jun 2017 16:24 UTC
2 points
0 comments2 min readLW link

Emer­gency learning

Stuart_Armstrong2 Jun 2017 16:23 UTC
1 point
0 comments4 min readLW link

Hu­mans as a truth channel

Stuart_Armstrong2 Jun 2017 16:22 UTC
1 point
0 comments2 min readLW link

All the in­differ­ence designs

Stuart_Armstrong2 Jun 2017 16:20 UTC
2 points
1 comment4 min readLW link

In­differ­ence and com­pen­satory rewards

Stuart_Armstrong2 Jun 2017 16:19 UTC
0 points
0 comments1 min readLW link

Coun­ter­fac­tu­ally un­in­fluence­able agents

Stuart_Armstrong2 Jun 2017 16:17 UTC
11 points
0 comments2 min readLW link

Trans­la­tion “coun­ter­fac­tual”

Stuart_Armstrong2 Jun 2017 16:16 UTC
0 points
0 comments2 min readLW link

Un­der­stand­ing the im­por­tant facts

Stuart_Armstrong2 Jun 2017 16:15 UTC
0 points
0 comments1 min readLW link

Low im­pact ver­sus low side effects

Stuart_Armstrong2 Jun 2017 16:14 UTC
1 point
0 comments2 min readLW link

Agents that don’t be­come maximisers

Stuart_Armstrong2 Jun 2017 16:13 UTC
0 points
0 comments3 min readLW link

AI safety: three hu­man prob­lems and one AI issue

Stuart_Armstrong2 Jun 2017 16:12 UTC
2 points
4 comments3 min readLW link

Op­ti­mi­sa­tion in ma­nipu­lat­ing hu­mans: en­g­ineered fa­nat­ics vs yes-men

Stuart_Armstrong2 Jun 2017 15:51 UTC
0 points
0 comments2 min readLW link

Diver­gent prefer­ences and meta-preferences

Stuart_Armstrong2 Jun 2017 15:51 UTC
9 points
0 comments3 min readLW link

Acausal trade: dou­ble decrease

Stuart_Armstrong2 Jun 2017 15:33 UTC
10 points
3 comments2 min readLW link

Acausal trade: differ­ent util­ities, differ­ent trades

Stuart_Armstrong2 Jun 2017 15:33 UTC
1 point
1 comment3 min readLW link

Acausal trade: uni­ver­sal util­ity, or sel­l­ing non-ex­is­tence in­surance too late

Stuart_Armstrong2 Jun 2017 15:33 UTC
1 point
1 comment3 min readLW link

Acausal trade: trade barriers

Stuart_Armstrong2 Jun 2017 15:32 UTC
0 points
1 comment2 min readLW link

Futarchy, Xrisks, and near misses

Stuart_Armstrong2 Jun 2017 8:02 UTC
1 point
0 comments1 min readLW link

Futarchy, Xrisks, and near misses

Stuart_Armstrong2 Jun 2017 8:02 UTC
10 points
10 comments1 min readLW link

Book recom­men­da­tion requests

ChristianKl1 Jun 2017 22:33 UTC
16 points
49 comments1 min readLW link

Why I am not cur­rently work­ing on the AAMLS agenda

jessicata1 Jun 2017 17:57 UTC
28 points
3 comments5 min readLW link

June 2017 Me­dia Thread

ArisKatsaris1 Jun 2017 6:17 UTC
2 points
35 comments1 min readLW link

Strong men are so­cial­ist—how to use a study’s own data to dis­prove it

Jacob Falkovich31 May 2017 4:18 UTC
9 points
5 comments1 min readLW link
(putanumonit.com)

Reg­u­la­tory lags for New Tech­nol­ogy [2013 notes]

gwern31 May 2017 1:27 UTC
9 points
5 comments69 min readLW link

Philo­soph­i­cal Parenthood

SquirrelInHell30 May 2017 14:09 UTC
1 point
25 comments1 min readLW link
(squirrelinhell.blogspot.com)

Diver­gent prefer­ences and meta-preferences

Stuart_Armstrong30 May 2017 7:33 UTC
6 points
1 comment2 min readLW link

Futarchy Fix

abramdemski30 May 2017 5:46 UTC
7 points
9 comments9 min readLW link

“AIXIjs: A Soft­ware Demo for Gen­eral Re­in­force­ment Learn­ing”, As­lanides 2017

gwern29 May 2017 21:09 UTC
7 points
1 comment1 min readLW link
(arxiv.org)

In­vi­ta­tion to com­ment on a draft on mul­ti­verse-wide co­op­er­a­tion via al­ter­na­tives to causal de­ci­sion the­ory (FDT/​UDT/​EDT/​...)

Caspar Oesterheld29 May 2017 8:34 UTC
6 points
7 comments1 min readLW link

Meetup : Syd­ney Ra­tion­al­ity—Pub meetup June

Elo29 May 2017 6:52 UTC
2 points
0 comments1 min readLW link

Open thread, May 29 - June 4, 2017

Thomas29 May 2017 6:13 UTC
4 points
84 comments1 min readLW link

In­ter­view on IQ, genes, and ge­netic en­g­ineer­ing with ex­pert (Hsu)

James_Miller28 May 2017 22:19 UTC
7 points
8 comments1 min readLW link
(www.youtube.com)

Bi-Weekly Ra­tional Feed

sapphire28 May 2017 17:12 UTC
21 points
7 comments8 min readLW link

Meetup : Melbourne So­cial Meetup: June

Maelin28 May 2017 10:10 UTC
1 point
0 comments1 min readLW link