A uni­ver­sal score for optimizers

levinJul 10, 2018, 11:52 PM
15 points
8 comments3 min readLW link

Bayesian Prob­a­bil­ity is for things that are Space-like Separated from You

Scott GarrabrantJul 10, 2018, 11:47 PM
86 points
22 comments2 min readLW link

Align­ment prob­lems for economists

Chris van MerwijkJul 10, 2018, 11:43 PM
5 points
2 comments2 min readLW link

Non-re­solve as Resolve

Linda LinseforsJul 10, 2018, 11:31 PM
15 points
1 comment2 min readLW link

A frame­work for think­ing about wireheading

theotherotheralexJul 10, 2018, 11:14 PM
15 points
4 comments1 min readLW link

Log­i­cal Uncer­tainty and Func­tional De­ci­sion Theory

swordsintoploughsharesJul 10, 2018, 11:08 PM
15 points
4 comments2 min readLW link

Re­peated (and im­proved) Sleep­ing Beauty problem

Linda LinseforsJul 10, 2018, 10:32 PM
12 points
5 comments2 min readLW link

Prob­a­bil­ity is fake, fre­quency is real

Linda LinseforsJul 10, 2018, 10:32 PM
12 points
7 comments1 min readLW link

Con­di­tion­ing, Coun­ter­fac­tu­als, Ex­plo­ra­tion, and Gears

DiffractorJul 10, 2018, 10:11 PM
28 points
1 comment5 min readLW link

Two agents can have the same source code and op­ti­mise differ­ent util­ity functions

Joar SkalseJul 10, 2018, 9:51 PM
11 points
11 comments1 min readLW link

The In­ten­tional Agency Experiment

Alexander Gietelink OldenzielJul 10, 2018, 8:32 PM
13 points
5 comments3 min readLW link

An­nounc­ing Align­men­tFo­rum.org Beta

RaemonJul 10, 2018, 8:19 PM
68 points
35 comments2 min readLW link

Choos­ing to Choose?

Daniel HerrmannJul 10, 2018, 8:15 PM
10 points
7 comments5 min readLW link

Study on what makes peo­ple ap­prove or con­demn mind up­load tech­nol­ogy; refer­ences LW

Kaj_SotalaJul 10, 2018, 5:14 PM
22 points
0 comments2 min readLW link
(www.nature.com)

How to par­ent more predictably

jefftkJul 10, 2018, 3:18 PM
78 points
1 comment4 min readLW link

Open Thread July 2018

nullJul 10, 2018, 2:51 PM
10 points
9 comments1 min readLW link

Three an­chor­ings: num­ber, at­ti­tude, and taste

Stuart_ArmstrongJul 10, 2018, 2:21 PM
14 points
4 comments2 min readLW link

The Dilemma of Worse Than Death Scenarios

arkaeikJul 10, 2018, 9:18 AM
14 points
18 comments4 min readLW link

New­comb’s Prob­lem In One Paragraph

Chris_LeongJul 10, 2018, 7:10 AM
7 points
0 comments1 min readLW link

Let­ting Go III: Unilat­eral or GTFO

johnswentworthJul 10, 2018, 6:26 AM
21 points
3 comments2 min readLW link

Syd­ney Ra­tion­al­ity Dojo—December

NextJul 10, 2018, 4:22 AM
1 point
0 comments1 min readLW link

Syd­ney Ra­tion­al­ity Dojo—November

NextJul 10, 2018, 4:20 AM
1 point
0 comments1 min readLW link

Syd­ney Ra­tion­al­ity Dojo—October

NextJul 10, 2018, 4:19 AM
1 point
0 comments1 min readLW link

Syd­ney Ra­tion­al­ity Dojo—September

NextJul 10, 2018, 4:12 AM
1 point
0 comments1 min readLW link

Syd­ney Ra­tion­al­ity Dojo—August

NextJul 10, 2018, 4:04 AM
1 point
0 comments1 min readLW link

Con­text Win­dows: A Model of Un­pro­duc­tive Disagreement

Zachary JacobiJul 10, 2018, 1:40 AM
4 points
2 comments5 min readLW link

Fun­da­men­tals of For­mal­i­sa­tion Level 5: For­mal Proof

philip_bJul 9, 2018, 8:55 PM
13 points
0 comments1 min readLW link

RAISE is look­ing for full-time con­tent developers

nullJul 9, 2018, 5:01 PM
22 points
5 comments1 min readLW link

Align­ment Newslet­ter #14

Rohin ShahJul 9, 2018, 4:20 PM
14 points
0 comments9 min readLW link
(mailchi.mp)

Math: Text­books and the DTP pipeline

Andrew QuinnJul 9, 2018, 3:09 PM
12 points
3 comments2 min readLW link

The Craft And The Codex

Paperclip MinimizerJul 9, 2018, 10:50 AM
12 points
7 commentsLW link
(slatestarcodex.com)

The Fermi Para­dox: What did Sand­berg, Drexler and Ord Really Dis­solve?

ShmiJul 8, 2018, 9:18 PM
47 points
28 comments5 min readLW link

An Ex­er­cise in Ap­plied Ra­tion­al­ity: A New Apartment

SableJul 8, 2018, 9:18 PM
8 points
9 comments1 min readLW link

Es­ti­mat­ing the con­se­quences of de­vice de­tec­tion tech

JsevillamolJul 8, 2018, 6:25 PM
27 points
4 comments7 min readLW link

Put­ting Log­a­r­ith­mic-Qual­ity Scales On Time

lionhearted (Sebastian Marshall)Jul 8, 2018, 3:00 PM
12 points
2 comments5 min readLW link

Au­to­matic for the people

technicalitiesJul 8, 2018, 2:23 PM
18 points
23 comments7 min readLW link

Sto­ries of Sum­mer Sols­tice

RaemonJul 8, 2018, 7:16 AM
53 points
12 comments6 min readLW link

How to aban­don reductionism

ExpoundingDhammaJul 8, 2018, 6:10 AM
−17 points
0 comments2 min readLW link

Book re­view: Pearl’s Book of Why

PeterMcCluskeyJul 7, 2018, 5:30 PM
69 points
8 comments6 min readLW link
(www.bayesianinvestor.com)

Over­com­ing Cling­i­ness in Im­pact Measures

IAFF-User-309Jul 7, 2018, 4:26 PM
0 points
0 comments1 min readLW link
(www.lesswrong.com)

Low Im­pact via Whitelisting

IAFF-User-309Jul 7, 2018, 4:25 PM
0 points
0 comments1 min readLW link
(www.lesswrong.com)

ob­vi­ous epipha­nies

nBrownJul 7, 2018, 3:05 AM
11 points
3 comments2 min readLW link

Towards dis­solv­ing the mys­tery of consciousness

GeometryOfTheShadowsJul 6, 2018, 9:36 PM
41 points
7 comments1 min readLW link

RFC: Men­tal phe­nom­ena in AGI alignment

Gordon Seidoh WorleyJul 5, 2018, 8:52 PM
12 points
16 comments5 min readLW link

Ge­offrey Miller on Polyamory and Mating

Jacob FalkovichJul 5, 2018, 8:01 PM
9 points
0 commentsLW link
(putanumonit.com)

Debt is an Anti-investment

Jacob FalkovichJul 5, 2018, 8:00 PM
48 points
42 comments6 min readLW link

An in­tro­duc­tion to worst-case AI safety

Tobias_BaumannJul 5, 2018, 4:09 PM
14 points
2 commentsLW link
(s-risks.org)

An op­ti­miza­tion pro­cess for demo­cratic organizations

selylindiJul 5, 2018, 3:34 PM
9 points
14 commentsLW link
(adelaybeingreborn.wordpress.com)

Wash­ing­ton, D.C.: Air & Space Museum

RobinZJul 5, 2018, 3:02 AM
8 points
0 comments1 min readLW link

On Authority

quanticleJul 5, 2018, 2:37 AM
13 points
1 comment1 min readLW link
(www.interfluidity.com)