En­vi­ron­ments for kil­ling AIs

Douglas_ReayMar 17, 2018, 3:23 PM
3 points
1 comment9 min readLW link

You can now log in with your LW1 cre­den­tials on LW2

habrykaMar 17, 2018, 5:56 AM
10 points
5 comments1 min readLW link

CoZE 3: Empiricism

alkjashMar 17, 2018, 4:10 AM
20 points
4 comments2 min readLW link
(radimentary.wordpress.com)

Rais­ing funds to es­tab­lish a new AI Safety charity

nullMar 17, 2018, 12:09 AM
57 points
9 comments5 min readLW link

The Ep­silon Fallacy

johnswentworthMar 17, 2018, 12:08 AM
93 points
21 comments7 min readLW link
(medium.com)

AI Sum­mer Fel­lows Program

colmMar 16, 2018, 9:57 PM
20 points
2 comments1 min readLW link

Dat­ing like a Pro

Jacob FalkovichMar 16, 2018, 9:09 PM
12 points
10 comments1 min readLW link
(putanumonit.com)

Rigged re­ward learning

Stuart_ArmstrongMar 16, 2018, 3:39 PM
1 point
0 comments2 min readLW link

Defect or Cooperate

Douglas_ReayMar 16, 2018, 2:12 PM
4 points
5 comments6 min readLW link

De­sign 3: Intentionality

alkjashMar 16, 2018, 4:30 AM
21 points
13 comments3 min readLW link
(radimentary.wordpress.com)

Cryp­tog­ra­phy/​Soft­ware Eng­ineer­ing Prob­lem: How to make LW 1.0 lo­gins work on LW 2.0

habrykaMar 16, 2018, 4:01 AM
8 points
17 comments2 min readLW link

The Costly Co­or­di­na­tion Mechanism of Com­mon Knowledge

Ben PaceMar 15, 2018, 8:20 PM
205 points
31 comments20 min readLW link2 reviews

Us­ing ly­ing to de­tect hu­man values

Stuart_ArmstrongMar 15, 2018, 11:41 AM
0 points
0 comments1 min readLW link
(www.lesserwrong.com)

Us­ing ly­ing to de­tect hu­man values

Stuart_ArmstrongMar 15, 2018, 11:37 AM
19 points
6 comments1 min readLW link

Up­com­ing sta­bil­ity of values

Stuart_ArmstrongMar 15, 2018, 11:36 AM
15 points
15 comments2 min readLW link

Values de­ter­mined by “stop­ping” properties

Stuart_ArmstrongMar 15, 2018, 10:53 AM
12 points
16 comments3 min readLW link

Don’t put all your eggs in one basket

Douglas_ReayMar 15, 2018, 8:07 AM
5 points
1 comment7 min readLW link

TAPs 3: Reductionism

alkjashMar 15, 2018, 5:20 AM
23 points
8 comments2 min readLW link
(radimentary.wordpress.com)

On Dualities

Chris_LeongMar 15, 2018, 2:10 AM
2 points
10 comments3 min readLW link

A Con­crete Multi-Step Var­i­ant of Dou­ble Crux I Have Used Suc­cess­fully

sapphireMar 15, 2018, 1:26 AM
16 points
4 comments2 min readLW link

Shadow

whpearsonMar 14, 2018, 9:13 PM
−1 points
6 comments1 min readLW link

The Build­ing Blocks of Interpretability

Ben PaceMar 14, 2018, 8:42 PM
8 points
1 comment1 min readLW link

LW Up­date 3/​14 – Com­mu­nity, Mark­down and More

RaemonMar 14, 2018, 6:29 PM
11 points
6 comments2 min readLW link

Ex­per­tise Exchange

ChristianKlMar 14, 2018, 6:04 PM
21 points
23 comments1 min readLW link

Op­ti­mum num­ber of sin­gle points of failure

Douglas_ReayMar 14, 2018, 1:30 PM
7 points
5 comments5 min readLW link

New Paper Ex­pand­ing on the Good­hart Taxonomy

Scott GarrabrantMar 14, 2018, 9:01 AM
17 points
4 commentsLW link
(arxiv.org)

Strength­en­ing the foun­da­tions un­der the Over­ton Win­dow with­out mov­ing it

KatjaGraceMar 14, 2018, 2:20 AM
12 points
7 comments3 min readLW link
(meteuphoric.wordpress.com)

Large Mam­mal BPF Prize Win­ning Announcement

JohnGreerMar 13, 2018, 11:48 PM
3 points
0 commentsLW link
(www.brainpreservation.org)

Re­quest for “Tests” for the MIRI Re­search Guide

HazardMar 13, 2018, 11:22 PM
28 points
14 comments1 min readLW link

Car­ing less

eukaryoteMar 13, 2018, 10:53 PM
73 points
24 comments4 min readLW link3 reviews

Look­ing and the no-self

ChristianKlMar 13, 2018, 7:39 PM
16 points
17 comments1 min readLW link

Yoda Timers 3: Speed

alkjashMar 13, 2018, 6:00 PM
20 points
13 comments2 min readLW link
(radimentary.wordpress.com)

A Devel­op­men­tal Frame­work for Rationality

lifelonglearnerMar 13, 2018, 1:36 AM
23 points
9 comments9 min readLW link

Bug Hunt 3

alkjashMar 13, 2018, 12:20 AM
26 points
14 comments3 min readLW link
(radimentary.wordpress.com)

Ap­pro­pri­ate­ness of Dis­cussing Ra­tion­al­ist Dis­course of a Poli­ti­cal Na­ture on LW?

Evan_GaensbauerMar 12, 2018, 11:21 PM
13 points
24 comments1 min readLW link

Avoid­ing AI Races Through Self-Regulation

Gordon Seidoh WorleyMar 12, 2018, 8:53 PM
7 points
2 comments8 min readLW link
(mapandterritory.org)

AI Align­ment Prize: Round 2 due March 31, 2018

ZviMar 12, 2018, 12:10 PM
28 points
2 comments3 min readLW link
(thezvi.wordpress.com)

Mul­ti­plic­ity of “en­light­en­ment” states and con­tem­pla­tive practices

Wei DaiMar 12, 2018, 8:15 AM
46 points
4 comments2 min readLW link

Should we re­move mark­down pars­ing from the com­ment ed­i­tor?

habrykaMar 12, 2018, 5:00 AM
9 points
14 comments1 min readLW link

A Tax­on­omy of Weird­ness

Evan ClarkMar 12, 2018, 2:33 AM
6 points
5 comments4 min readLW link

ESPR 2018 Ap­pli­ca­tions Are Open!

lifelonglearnerMar 12, 2018, 12:02 AM
2 points
0 comments1 min readLW link

Leav­ing beta: Vot­ing on mov­ing to LessWrong.com

VaniverMar 11, 2018, 11:40 PM
10 points
38 comments2 min readLW link

Leav­ing beta: Vot­ing on mov­ing to LessWrong.com

VaniverMar 11, 2018, 10:53 PM
57 points
65 comments2 min readLW link

Edi­tor Mini-Guide

Ben PaceMar 11, 2018, 8:58 PM
22 points
62 comments2 min readLW link

Mur­phy’s Quest Postmorterm

alkjashMar 11, 2018, 8:10 PM
28 points
10 comments6 min readLW link
(radimentary.wordpress.com)

ESPR 2018 Ap­pli­ca­tions Are Open

lifelonglearnerMar 11, 2018, 8:07 PM
9 points
4 comments1 min readLW link

Types of Con­fu­sion Experiences

HazardMar 11, 2018, 2:32 PM
13 points
0 comments2 min readLW link

Mur­phy’s Quest Ch 13: Ex­is­ten­tial Risk

alkjashMar 11, 2018, 7:10 AM
22 points
5 comments2 min readLW link
(radimentary.wordpress.com)

Ke­gan and Cul­ti­vat­ing Compassion

lifelonglearnerMar 11, 2018, 1:32 AM
18 points
4 comments6 min readLW link

Misery Pits

AlicornMar 10, 2018, 11:50 PM
47 points
23 comments2 min readLW link