Us­ing ra­tio­nal­ity to de­bug Ma­chine Learning

Dr_ManhattanApr 10, 2018, 8:03 PM
20 points
3 comments1 min readLW link
(amid.fish)

The limits of corrigibility

Stuart_ArmstrongApr 10, 2018, 10:49 AM
27 points
9 comments4 min readLW link

Trust­wor­thy Computing

Douglas_ReayApr 10, 2018, 7:55 AM
9 points
1 comment6 min readLW link

An­nounc­ing the Align­ment Newsletter

Rohin ShahApr 9, 2018, 9:16 PM
29 points
3 comments1 min readLW link

OpenAI charter

wunanApr 9, 2018, 9:02 PM
17 points
2 commentsLW link
(blog.openai.com)

Role-play­ing game based on HPMOR

Alexander230Apr 9, 2018, 6:19 PM
3 points
0 comments1 min readLW link

The Align­ment Newslet­ter #1: 04/​09/​18

Rohin ShahApr 9, 2018, 4:00 PM
12 points
3 comments4 min readLW link

Trust the (lo­cal) expert

rkApr 9, 2018, 10:22 AM
14 points
12 comments7 min readLW link

How do we change our minds? A meetup blueprint

ChristianKlApr 9, 2018, 7:58 AM
10 points
0 comments4 min readLW link

Why fo­cus on AI?

nomoreApr 8, 2018, 10:58 PM
0 points
6 comments1 min readLW link

Cri­tique my Model: The EV of AGI to Selfish Individuals

ozziegooenApr 8, 2018, 8:04 PM
19 points
9 comments4 min readLW link

BYOL (Buy Your Own Lunch)

JohnGreerApr 8, 2018, 7:32 PM
1 point
8 comments2 min readLW link

I de­sire U, grpfrt, but I won’t eat U.

Jacob FalkovichApr 8, 2018, 7:19 PM
6 points
1 comment1 min readLW link

GreaterWrong—more new fea­tures & enhancements

Said AchmizApr 7, 2018, 8:41 PM
9 points
1 comment1 min readLW link

Mean­ing and Mo­ral Foun­da­tions Theory

bryjnarApr 7, 2018, 5:59 PM
14 points
8 comments2 min readLW link

No Con­stant Distri­bu­tion Can be a Log­i­cal Inductor

DiffractorApr 7, 2018, 9:09 AM
22 points
1 comment2 min readLW link

Lo­cal Val­idity as a Key to San­ity and Civilization

Eliezer YudkowskyApr 7, 2018, 4:25 AM
221 points
68 comments13 min readLW link5 reviews

Sur­vey: Help Us Re­search Co­or­di­na­tion Prob­lems In The Ra­tion­al­ist/​EA Community

namespaceApr 6, 2018, 11:29 PM
18 points
13 comments1 min readLW link

Is Rhetoric Worth Learn­ing?

sarahconstantinApr 6, 2018, 10:03 PM
66 points
56 comments2 min readLW link

Open Thread April 2018

Gunnar_ZarnckeApr 6, 2018, 9:02 PM
7 points
25 comments1 min readLW link

LW Up­date 04/​06/​18 – QM Se­quence Updated

Ben PaceApr 6, 2018, 8:53 AM
12 points
3 comments1 min readLW link

Free­lance plat­form, free­lance mar­ket­place plat­form, Mar­ket­place script

IAFF-User-292Apr 6, 2018, 7:15 AM
0 points
0 comments1 min readLW link
(www.agriya.com)

A Test of Faith

Serpent-StareApr 6, 2018, 4:36 AM
6 points
2 comments7 min readLW link

Boxes for Our Thoughts

TueskesApr 6, 2018, 1:15 AM
1 point
0 comments2 min readLW link
(contexturalthought.wordpress.com)

Cat­e­go­riz­ing Love: How hav­ing more words for love might make it less scary

squidiousApr 5, 2018, 11:10 PM
15 points
2 comments3 min readLW link
(opalsandbonobos.blogspot.com)

Re­view of CZEA “In­tense EA Week­end” re­treat

Jan_KulveitApr 5, 2018, 11:04 PM
26 points
1 comment8 min readLW link
(effective-altruism.com)

Bounds of Attention

squidiousApr 5, 2018, 10:53 PM
26 points
1 comment2 min readLW link

Mo­ral Uncertainty

Mati_RoyApr 5, 2018, 6:59 PM
2 points
0 comments1 min readLW link

Schel­ling Day

Mati_RoyApr 5, 2018, 6:56 PM
2 points
0 comments1 min readLW link

Fun The­ory—Group Discussion

Mati_RoyApr 5, 2018, 6:54 PM
2 points
0 comments1 min readLW link

Against Oc­cam’s Razor

zulupineappleApr 5, 2018, 5:59 PM
4 points
20 comments1 min readLW link

Adult Neu­ro­ge­n­e­sis – A Pointed Review

Scott AlexanderApr 5, 2018, 4:50 AM
55 points
17 comments11 min readLW link
(slatestarcodex.com)

Wash­ing­ton, D.C.: Less Wrong

RobinZApr 5, 2018, 3:05 AM
2 points
0 comments1 min readLW link

Death in Groups

ryan_bApr 5, 2018, 12:45 AM
31 points
20 comments2 min readLW link

Com­pe­ti­tion for Power

Samo BurjaApr 4, 2018, 5:10 PM
17 points
8 comments9 min readLW link
(medium.com)

Real­is­tic thought experiments

KatjaGraceApr 4, 2018, 1:50 AM
26 points
8 comments1 min readLW link
(meteuphoric.wordpress.com)

HPMoE 3

alkjashApr 4, 2018, 1:00 AM
4 points
0 comments1 min readLW link
(radimentary.wordpress.com)

An Ar­gu­ment For Pri­ori­tiz­ing: “Pos­i­tively Shap­ing the Devel­op­ment of Crypto-as­sets”

rhys_lindmarkApr 3, 2018, 10:12 PM
3 points
1 commentLW link
(effective-altruism.com)

Speci­fi­ca­tion gam­ing ex­am­ples in AI

VikaApr 3, 2018, 12:30 PM
47 points
9 comments1 min readLW link2 reviews

[Draft for com­ment­ing] Near-Term AI risks predictions

avturchinApr 3, 2018, 10:29 AM
6 points
6 comments1 min readLW link

Uny­ield­ing Yoda Timers: Tak­ing the Ham­mer­time Fi­nal Exam

TurnTroutApr 3, 2018, 2:38 AM
16 points
3 comments1 min readLW link

Mus­ings on Exploration

DiffractorApr 3, 2018, 2:15 AM
1 point
4 comments6 min readLW link

Suffer­ing and In­tractable Pain

Gordon Seidoh WorleyApr 3, 2018, 1:05 AM
11 points
4 comments7 min readLW link
(mapandterritory.org)

Why Karma 2.0? (A Kab­bal­is­tic Ex­pla­na­tion)

Ben PaceApr 2, 2018, 8:43 PM
15 points
1 comment1 min readLW link

Brno: Far fu­ture, ex­is­ten­tial risk and AI safety

Jan_KulveitApr 2, 2018, 7:11 PM
3 points
0 comments1 min readLW link

HPMoE 2

alkjashApr 2, 2018, 5:30 AM
6 points
3 comments1 min readLW link
(radimentary.wordpress.com)

In­ter­nal Diet Crux

Jacob FalkovichApr 2, 2018, 5:05 AM
45 points
8 comments6 min readLW link

New York Ra­tion­al­ist Seder

Jacob FalkovichApr 2, 2018, 12:24 AM
3 points
0 comments1 min readLW link

Can cor­rigi­bil­ity be learned safely?

Wei DaiApr 1, 2018, 11:07 PM
35 points
115 comments4 min readLW link

Global in­sect de­clines: Why aren’t we all dead yet?

eukaryoteApr 1, 2018, 8:38 PM
28 points
26 comments1 min readLW link