UDT can learn an­thropic probabilities

cousin_itJun 24, 2018, 6:04 PM
54 points
10 comments3 min readLW link

Con­cep­tual is­sues in AI safety: the paradig­matic gap

vedevazzJun 24, 2018, 3:09 PM
33 points
0 commentsLW link
(www.foldl.me)

Open Thread

Bound_upJun 23, 2018, 10:49 PM
8 points
17 commentsLW link

What am I? A bit of po­etic prose.

AureliusGrayJun 23, 2018, 5:19 PM
−10 points
0 comments1 min readLW link

In­for­ma­tional haz­ards and the cost-effec­tive­ness of open dis­cus­sion of catas­trophic risks

avturchinJun 23, 2018, 1:31 PM
−2 points
11 comments4 min readLW link
(effective-altruism.com)

Ex­tend­ing the Pri­vate Lan­guage Argument

Ashwin KumarJun 23, 2018, 9:07 AM
−4 points
10 comments3 min readLW link
(medium.com)

Dojo: Al­gorith­mic Creativity—Chap­ter 2

ChriswaterguyJun 23, 2018, 5:42 AM
9 points
0 comments1 min readLW link

Two pre­scrip­tions for fix­ing a pro­ce­du­ral/​declar­a­tive knowl­edge mis­match.

Andrew QuinnJun 22, 2018, 10:17 PM
31 points
4 comments3 min readLW link

An­throp­ics: Where does Less Wrong lie?

Chris_LeongJun 22, 2018, 10:27 AM
15 points
7 comments1 min readLW link

CFAR Reunion

CFAR TeamJun 21, 2018, 8:35 PM
42 points
1 comment1 min readLW link

Ben Hoff­man’s donor recommendations

Rob BensingerJun 21, 2018, 4:02 PM
41 points
19 comments1 min readLW link

Wash­ing­ton, D.C.: Fun & Games

RobinZJun 21, 2018, 3:21 AM
8 points
0 comments1 min readLW link

Does any­one use ad­vanced me­dia pro­jects?

ryan_bJun 20, 2018, 11:33 PM
33 points
5 comments1 min readLW link

Games in Kocherga club: Fal­la­cy­ma­nia, Tower of Chaos, Scien­tific Discovery

Alexander230Jun 20, 2018, 10:05 PM
9 points
0 comments1 min readLW link

Loss aver­sion is not what you think it is

Paperclip MinimizerJun 20, 2018, 3:56 PM
13 points
14 commentsLW link
(www.basilhalperin.com)

An­throp­ics and Fermi

Stuart_ArmstrongJun 20, 2018, 1:04 PM
26 points
20 comments3 min readLW link

Du­pli­ca­tion ver­sus probability

Stuart_ArmstrongJun 20, 2018, 12:18 PM
27 points
12 comments2 min readLW link

Wire­head your Chickens

ShmiJun 20, 2018, 5:49 AM
86 points
53 comments2 min readLW link

Ge­offrey Miller on Re­search and Poli­tics in Psychology

Jacob FalkovichJun 19, 2018, 9:03 PM
7 points
0 comments1 min readLW link
(putanumonit.com)

Para­doxes in all an­thropic probabilities

Stuart_ArmstrongJun 19, 2018, 3:31 PM
22 points
26 comments3 min readLW link

Prob­lem Solv­ing with Mazes and Crayon

johnswentworthJun 19, 2018, 6:15 AM
152 points
28 comments7 min readLW link

Order from Ran­dom­ness: Order­ing the Uni­verse of Ran­dom Numbers

ShmiJun 19, 2018, 5:37 AM
15 points
7 comments3 min readLW link

Sleep­ing Beauty Not Resolved

Chris_LeongJun 19, 2018, 4:46 AM
18 points
53 comments8 min readLW link

LessWrong is hiring

RaemonJun 19, 2018, 1:38 AM
71 points
7 comments1 min readLW link

The Align­ment Newslet­ter #11: 06/​18/​18

Rohin ShahJun 18, 2018, 4:00 PM
8 points
0 comments10 min readLW link

Why Destruc­tive Value Cap­ture?

ZviJun 18, 2018, 12:20 PM
29 points
13 comments4 min readLW link
(thezvi.wordpress.com)

Pri­vacy: Defin­ing Yourself

LulieJun 18, 2018, 2:15 AM
39 points
5 comments3 min readLW link

In Defense of Am­bigu­ous Problems

Chris_LeongJun 17, 2018, 7:40 AM
6 points
6 comments2 min readLW link

Fun­da­men­tals of For­mal­i­sa­tion Level 4: For­mal Se­man­tics Basics

philip_bJun 16, 2018, 7:09 PM
12 points
0 comments1 min readLW link

Us­ing the uni­ver­sal prior for log­i­cal uncertainty

cousin_itJun 16, 2018, 2:11 PM
0 points
0 comments1 min readLW link
(www.greaterwrong.com)

How many philoso­phers ac­cept the or­thog­o­nal­ity the­sis ? Ev­i­dence from the PhilPapers survey

Paperclip MinimizerJun 16, 2018, 12:11 PM
3 points
26 comments3 min readLW link

Wor­ry­ing about the Vase: Whitelisting

TurnTroutJun 16, 2018, 2:17 AM
73 points
26 comments11 min readLW link

Merg­ing accounts

Chris_LeongJun 16, 2018, 12:45 AM
5 points
2 comments1 min readLW link

The Cu­ri­ous Pri­soner Puzzle

Chris_LeongJun 16, 2018, 12:40 AM
4 points
14 comments1 min readLW link

Ge­offrey Miller on Effec­tive Altru­ism and Rationality

Jacob FalkovichJun 15, 2018, 5:05 PM
19 points
0 comments1 min readLW link
(putanumonit.com)

Aligned AI May Depend on Mo­ral Facts

Gordon Seidoh WorleyJun 15, 2018, 1:33 AM
8 points
11 comments1 min readLW link

SIAM Lec­ture: How Para­doxes Shape Math­e­mat­ics and Give Us Self-Ver­ify­ing Com­puter Programs

ldsrrsJun 14, 2018, 8:58 PM
3 points
0 comments1 min readLW link
(meetings.siam.org)

We Agree: Speeches All Around!

SebastianG Jun 14, 2018, 5:53 PM
37 points
19 comments2 min readLW link

Weak ar­gu­ments against the uni­ver­sal prior be­ing malign

X4vierJun 14, 2018, 5:11 PM
50 points
23 comments3 min readLW link

Notes on a re­cent wave of spam

rossryJun 14, 2018, 3:39 PM
11 points
2 comments1 min readLW link

Log­i­cal In­duc­tor Tiling and Why it’s Hard

DiffractorJun 14, 2018, 6:34 AM
4 points
0 comments12 min readLW link

Wash­ing­ton, D.C.: Anxiety

RobinZJun 14, 2018, 1:17 AM
15 points
0 comments1 min readLW link

An­throp­ics made easy?

Stuart_ArmstrongJun 14, 2018, 12:56 AM
32 points
61 comments6 min readLW link

Coun­ter­fac­tual Mug­ging Poker Game

Scott GarrabrantJun 13, 2018, 11:34 PM
126 points
4 comments1 min readLW link

On the Chatham House Rule

Scott GarrabrantJun 13, 2018, 9:41 PM
68 points
25 comments4 min readLW link1 review

[Math] Towards Proof Writ­ing as a Skill In Itself

Andrew QuinnJun 13, 2018, 4:39 AM
25 points
8 comments2 min readLW link

To­day a Tragedy

Logan RiggsJun 13, 2018, 1:58 AM
54 points
17 comments1 min readLW link

Episte­molog­i­cal Braces

musicmage4114Jun 12, 2018, 10:01 PM
1 point
2 comments6 min readLW link

LW Up­date 2018-06-11 – Vul­can Re­fac­tor, Karma Over­haul, Colored Links, Moder­a­tion Log

RaemonJun 12, 2018, 12:49 AM
32 points
34 comments3 min readLW link

Ad­miring the Guts of Things.

MelkorJun 11, 2018, 11:12 PM
22 points
1 comment3 min readLW link