Risks from Learned Op­ti­miza­tion: Introduction

May 31, 2019, 11:44 PM
187 points
42 comments12 min readLW link3 reviews

Site Guide: Per­sonal Blog­posts vs Front­page Posts

RubyMay 31, 2019, 11:08 PM
73 points
15 comments2 min readLW link

When Ob­ser­va­tion Beats Experiment

johnswentworthMay 31, 2019, 10:58 PM
19 points
7 comments1 min readLW link

[Question] How to de­ter­mine if my sym­pa­thetic or my parasym­pa­thetic ner­vous sys­tem is cur­rently dom­i­nant?

philip_bMay 31, 2019, 8:40 PM
20 points
5 comments1 min readLW link

[Question] What is the best on­line com­mu­nity for ques­tions about AI ca­pa­bil­ities?

Ben GoldhaberMay 31, 2019, 3:38 PM
4 points
2 comments1 min readLW link

Ego­ism In Disguise

Wes FMay 31, 2019, 2:40 PM
1 point
12 comments4 min readLW link

Lonelinesses

Jacob FalkovichMay 31, 2019, 1:55 PM
53 points
5 comments5 min readLW link

[Question] How would you ad­vise a peer-sup­ported virtues-ori­ented self-help group?

David GrossMay 31, 2019, 12:20 AM
15 points
0 comments1 min readLW link

If you are a Ma­chine. A shock­ing find­ing.

Conner_MasolinMay 30, 2019, 11:38 PM
−3 points
0 comments1 min readLW link

Uncer­tainty ver­sus fuzzi­ness ver­sus ex­trap­o­la­tion desiderata

Stuart_ArmstrongMay 30, 2019, 1:52 PM
29 points
8 comments4 min readLW link

In­finity is an ad­jec­tive like pos­i­tive rather than an amount

SliderMay 30, 2019, 1:22 PM
0 points
10 comments2 min readLW link

Quotes from Mo­ral Mazes

ZviMay 30, 2019, 11:50 AM
114 points
27 comments53 min readLW link
(thezvi.wordpress.com)

OECD agenda [Link]

ThomasMay 30, 2019, 9:51 AM
1 point
1 comment1 min readLW link

Archive of all LW es­say contests

DirectedEvolutionMay 30, 2019, 6:40 AM
12 points
0 comments1 min readLW link

How to find a lost phone with dead bat­tery, us­ing Google Lo­ca­tion His­tory Takeout

Wei DaiMay 30, 2019, 4:56 AM
53 points
5 comments1 min readLW link

South Bay Meetup

DavidFriedmanMay 30, 2019, 2:32 AM
4 points
0 commentsLW link

Seek­ing sug­ges­tions for EA cash-prize contest

DirectedEvolutionMay 29, 2019, 8:44 PM
14 points
1 comment1 min readLW link

[Question] What is re­quired to run a psy­chol­ogy study?

RaemonMay 29, 2019, 6:38 AM
30 points
14 comments1 min readLW link

Drown­ing chil­dren are rare

BenquoMay 28, 2019, 7:27 PM
10 points
173 comments5 min readLW link
(benjaminrosshoffman.com)

Ev­i­dence for Con­nec­tion Theory

Evan_GaensbauerMay 28, 2019, 5:06 PM
14 points
13 comments1 min readLW link
(www.scribd.com)

A shift in ar­gu­ments for AI risk

Richard_NgoMay 28, 2019, 1:47 PM
32 points
7 comments1 min readLW link
(fragile-credences.github.io)

[Question] What should ra­tio­nal­ists think about the re­cent claims that air force pi­lots ob­served UFOs?

avturchinMay 27, 2019, 10:02 PM
12 points
28 comments1 min readLW link

[Question] Was CFAR always in­tended to be a dis­tinct or­ga­ni­za­tion from MIRI?

Evan_GaensbauerMay 27, 2019, 4:58 PM
7 points
3 comments1 min readLW link

Von Neu­mann’s cri­tique of au­tomata the­ory and logic in com­puter science

Ben PaceMay 26, 2019, 4:14 AM
29 points
4 comments3 min readLW link

[Question] Is AI safety doomed in the long term?

JakeHMay 26, 2019, 2:30 AM
−1 points
11 comments1 min readLW link

Micro feed­back loops and learning

Swimmer963 (Miranda Dixon-Luinenburg) May 26, 2019, 12:50 AM
53 points
13 comments6 min readLW link

God is an AGI we make in the fu­ture.

AkkaMay 25, 2019, 3:10 AM
−14 points
4 comments5 min readLW link

Say Wrong Things

Gordon Seidoh WorleyMay 24, 2019, 10:11 PM
116 points
13 comments4 min readLW link

Laws of John Wick

ZviMay 24, 2019, 3:20 PM
30 points
1 comment6 min readLW link
(thezvi.wordpress.com)

Learn­ing-by-do­ing AI Safety Re­search workshop

Linda LinseforsMay 24, 2019, 9:42 AM
11 points
1 comment2 min readLW link

Sepa­ra­tion of Concerns

abramdemskiMay 23, 2019, 9:47 PM
67 points
30 comments6 min readLW link

Moscow LW meetup in “Nauchka” library

Alexander230May 23, 2019, 8:39 PM
3 points
0 comments1 min readLW link

Why the em­piri­cal re­sults of the Trav­el­ler’s Dilemma de­vi­ate strongly away from the Nash Equil­ibrium and seems to be close to the so­cial op­ti­mum?

RocksBasilMay 23, 2019, 12:36 PM
7 points
15 comments3 min readLW link

Epi­sode 5 of Tsuyoku Nar­i­tai (the ‘be­com­ing stronger’ pod­cast): The Stance

Bae's TheoremMay 23, 2019, 4:15 AM
3 points
0 comments1 min readLW link

Does the Higgs-bo­son ex­ist?

ShmiMay 23, 2019, 1:53 AM
7 points
48 comments1 min readLW link
(backreaction.blogspot.com)

Free will as an ap­pear­ance to others

Yuxi_LiuMay 22, 2019, 11:57 PM
12 points
21 comments2 min readLW link

And the AI would have got away with it too, if...

Stuart_ArmstrongMay 22, 2019, 9:35 PM
75 points
7 comments1 min readLW link

Cog­ni­tion and In­tractabil­ity by Rooij, Blokpoel, Kwisthout, Wareham

bhishmaMay 22, 2019, 6:55 PM
3 points
0 comments1 min readLW link
(www.cambridge.org)

[Question] What is your per­sonal ex­pe­rience with “hav­ing a mean­ingful life”?

HazardMay 22, 2019, 2:03 PM
22 points
26 comments2 min readLW link

SSC Paris Meetup

fbretonMay 22, 2019, 1:48 PM
2 points
0 comments1 min readLW link

Schel­ling Fences ver­sus Marginal Thinking

DavidmanheimMay 22, 2019, 10:22 AM
23 points
8 comments3 min readLW link

[Question] Where are peo­ple think­ing and talk­ing about global co­or­di­na­tion for AI safety?

Wei DaiMay 22, 2019, 6:24 AM
112 points
22 comments1 min readLW link

A War of Ants and Grasshoppers

BenquoMay 22, 2019, 5:57 AM
17 points
21 comments1 min readLW link
(benjaminrosshoffman.com)

Dis­course Norms: Jus­tify or Re­tract Accusations

Davis_KingsleyMay 22, 2019, 1:49 AM
8 points
24 comments1 min readLW link

Con­straints & Slack­ness Rea­son­ing Exercises

johnswentworthMay 21, 2019, 10:53 PM
42 points
3 comments6 min readLW link

A Quick Tax­on­omy of Ar­gu­ments for The­o­ret­i­cal Eng­ineer­ing Capabilities

RubyMay 21, 2019, 10:38 PM
30 points
1 comment3 min readLW link

[Question] Could hu­man­ity ac­com­plish ev­ery­thing which na­ture has? Why might this not be the case?

RubyMay 21, 2019, 9:03 PM
8 points
0 comments1 min readLW link

[Question] Could hu­man­ity ever achieve atom­i­cally pre­cise man­u­fac­tur­ing (APM)? What about a much-smarter-than-hu­man-level in­tel­li­gence?

RubyMay 21, 2019, 9:00 PM
8 points
0 commentsLW link

TAISU—Tech­ni­cal AI Safety Unconference

Linda LinseforsMay 21, 2019, 6:34 PM
15 points
15 comments1 min readLW link

Go Do Something

Davis_KingsleyMay 21, 2019, 3:42 PM
38 points
25 comments1 min readLW link