On Gen­der and Emo­tional Support

squidiousMay 7, 2018, 10:37 PM
17 points
3 comments5 min readLW link

What are Trig­ger-Ac­tion Plans (TAPs)?

LulieMay 7, 2018, 6:28 PM
18 points
9 comments4 min readLW link

The Align­ment Newslet­ter #5: 05/​07/​18

Rohin ShahMay 7, 2018, 4:00 PM
8 points
0 comments7 min readLW link

Philos­o­phy of Mind: Umwelt, In­for­ma­tion, Value, and In­for­ma­tion-Value

Will LorcaMay 7, 2018, 11:55 AM
10 points
2 comments5 min readLW link

Every­thing I ever needed to know, I learned from World of War­craft: In­cen­tives and rewards

Said AchmizMay 7, 2018, 6:44 AM
25 points
6 comments9 min readLW link
(blog.obormot.net)

Fuzzy Boundaries, Real Concepts

orthonormalMay 7, 2018, 3:39 AM
27 points
8 comments7 min readLW link

LW Open Source – Get­ting Started [warn­ing: not up-to-date]

RaemonMay 6, 2018, 11:28 PM
35 points
32 comments4 min readLW link

LW Up­date 5/​6/​2018 – Meta and Moderation

RaemonMay 6, 2018, 8:33 PM
12 points
14 comments1 min readLW link

Ad­vo­cat­ing for fac­tual ad­vo­cacy

JsevillamolMay 6, 2018, 8:47 AM
12 points
6 comments1 min readLW link

Pre­dict­ing Fu­ture Morality

ESRogsMay 6, 2018, 7:17 AM
13 points
21 comments1 min readLW link

[Paper]: Clas­sifi­ca­tion of global catas­trophic risks con­nected with ar­tifi­cial intelligence

avturchinMay 6, 2018, 6:42 AM
1 point
0 commentsLW link
(link.springer.com)

Look­ing for AI Safety Ex­perts to Provide High Level Guidance for RAISE

OferMay 6, 2018, 2:06 AM
17 points
5 comments1 min readLW link

Open ques­tion: are min­i­mal cir­cuits dae­mon-free?

paulfchristianoMay 5, 2018, 10:40 PM
83 points
70 comments2 min readLW link1 review

5-minute timer tool

GustMay 5, 2018, 3:58 PM
7 points
1 comment1 min readLW link
(gusbicalho.github.io)

A pos­si­ble solu­tion to the Fermi Paradox

Rafael HarthMay 5, 2018, 2:56 PM
4 points
5 comments3 min readLW link

The Sheep­skin Effect

ZviMay 5, 2018, 12:10 PM
10 points
4 comments5 min readLW link
(thezvi.wordpress.com)

AI Safety via Debate

ESRogsMay 5, 2018, 2:11 AM
27 points
14 comments1 min readLW link
(blog.openai.com)

Fun­da­men­tals of For­mal­i­sa­tion level 1: Ba­sic Logic

nullMay 4, 2018, 1:01 PM
8 points
4 comments1 min readLW link

AGI Safety Liter­a­ture Re­view (Ever­itt, Lea & Hut­ter 2018)

Kaj_SotalaMay 4, 2018, 8:56 AM
14 points
1 comment1 min readLW link
(arxiv.org)

Bayes’ Law is About Mul­ti­ple Hy­poth­e­sis Testing

abramdemskiMay 4, 2018, 5:31 AM
36 points
5 comments5 min readLW link

[LINK] How to write a dom­i­nant as­surance con­tract on the Ethereum blockchain

fortyeridaniaMay 4, 2018, 3:44 AM
1 point
0 commentsLW link
(programtheblockchain.com)

Words, Lo­cally Defined

abramdemskiMay 3, 2018, 11:26 PM
19 points
27 comments3 min readLW link

Con­founded No Longer: In­sights from ‘All of Statis­tics’

TurnTroutMay 3, 2018, 10:56 PM
21 points
7 comments10 min readLW link

Every­thing I ever needed to know, I learned from World of War­craft: Good­hart’s law

Said AchmizMay 3, 2018, 4:33 PM
37 points
21 comments6 min readLW link1 review
(blog.obormot.net)

Rig­ging is a form of wireheading

Stuart_ArmstrongMay 3, 2018, 12:50 PM
11 points
2 comments1 min readLW link

Mo­ral frame­works and the Har­ris/​Klein debate

lincolnquirkMay 3, 2018, 9:49 AM
5 points
14 comments1 min readLW link

Dun­can Sa­bien: “In Defense of Punch Bug”

Davis_KingsleyMay 3, 2018, 8:26 AM
30 points
187 comments1 min readLW link
(medium.com)

Doubts about Updatelessness

DiffractorMay 3, 2018, 5:44 AM
9 points
3 comments8 min readLW link

Ra­tional Feed: Last Month’s Best Posts

sapphireMay 2, 2018, 6:19 PM
16 points
0 comments2 min readLW link

Please Take the 2018 Effec­tive Altru­ism Sur­vey!

Peter WildefordMay 2, 2018, 7:58 AM
14 points
0 comments1 min readLW link

Brief com­ment on front­page/​per­sonal distinction

Ben PaceMay 1, 2018, 6:53 PM
21 points
3 comments1 min readLW link

Eight poli­ti­cal de­mands that I hope we can agree on

ChristianKlMay 1, 2018, 4:59 PM
4 points
35 comments1 min readLW link

Open Thread May 2018

EloMay 1, 2018, 6:23 AM
9 points
21 comments1 min readLW link

Ikaxas’ Ham­mer­time Fi­nal Exam

Vaughn PapenhausenMay 1, 2018, 3:30 AM
10 points
2 comments1 min readLW link

Thoughts on the REACH Patreon

RaemonApr 30, 2018, 8:51 PM
36 points
21 comments20 min readLW link

Wash­ing­ton, D.C.: To-Do List Hacking

RobinZApr 30, 2018, 7:23 PM
5 points
0 comments1 min readLW link

Pre­dic­tion Con­test 2018

jbeshirApr 30, 2018, 6:26 PM
9 points
4 comments3 min readLW link

In­ter­nal­iz­ing In­ter­nal Dou­ble Crux

TurnTroutApr 30, 2018, 6:23 PM
35 points
12 comments4 min readLW link

A Few Tips on How to Gen­er­ally Feel Bet­ter (and Avoid Headaches)

moridinamaelApr 30, 2018, 4:02 PM
28 points
12 comments4 min readLW link

The Align­ment Newslet­ter #4: 04/​30/​18

Rohin ShahApr 30, 2018, 4:00 PM
8 points
0 comments3 min readLW link

Begin­ning Ma­chine Learning

crybxApr 30, 2018, 3:54 PM
12 points
4 comments6 min readLW link

Are long-term in­vest­ments a good way to help the fu­ture?

DacynApr 30, 2018, 2:41 PM
10 points
50 comments3 min readLW link

Soon: a weekly AI Safety pre­req­ui­sites mod­ule on LessWrong

nullApr 30, 2018, 1:23 PM
35 points
10 comments1 min readLW link

Re­search: Res­cuers dur­ing the Holocaust

Martin SustrikApr 30, 2018, 6:15 AM
97 points
14 comments9 min readLW link1 review

Give praise

nullApr 29, 2018, 9:00 PM
77 points
87 comments1 min readLW link1 review

Does Think­ing Hard Hurt Your Brain?

RaemonApr 29, 2018, 6:56 PM
19 points
38 comments1 min readLW link

The Case Against Ed­u­ca­tion: Split­ting the Ed­u­ca­tion Premium Pie and Con­sid­er­ing IQ

ZviApr 29, 2018, 12:40 PM
7 points
5 comments9 min readLW link
(thezvi.wordpress.com)

Levels of AI Self-Im­prove­ment

avturchinApr 29, 2018, 11:45 AM
11 points
1 comment39 min readLW link

Ineffi­cient Doesn’t Mean Indifferent

ZviApr 29, 2018, 11:30 AM
39 points
17 comments3 min readLW link
(thezvi.wordpress.com)

SSC South Bay Meetup

DavidFriedmanApr 29, 2018, 7:22 AM
6 points
2 commentsLW link