All200520062007200820092010201120122013201420152016201720182019202020212022202320242025
AllJanFebMarAprMayJunJulAugSepOctNovDec

Strong Votes [Up­date: De­ployed]

RaemonJun 1, 2018, 9:03 PM
94 points
93 comments2 min readLW link

The Learn­ing-The­o­retic AI Align­ment Re­search Agenda

Vanessa KosoyJul 4, 2018, 9:53 AM
94 points
37 comments32 min readLW link

Don’t Get Dis­tracted by the Boilerplate

johnswentworthJul 26, 2018, 2:15 AM
93 points
19 comments2 min readLW link

Up­date the best text­books on ev­ery sub­ject list

ryan_bNov 8, 2018, 8:54 PM
93 points
14 comments1 min readLW link

An­nounce­ment: AI al­ign­ment prize round 3 win­ners and next round

cousin_itJul 15, 2018, 7:40 AM
93 points
7 comments1 min readLW link

Pre­limi­nary thoughts on moral weight

lukeprogAug 13, 2018, 11:45 PM
93 points
49 comments8 min readLW link2 reviews

Toward a New Tech­ni­cal Ex­pla­na­tion of Tech­ni­cal Explanation

abramdemskiFeb 16, 2018, 12:44 AM
92 points
36 comments18 min readLW link1 review

Un­der­stand­ing is translation

cousin_itMay 28, 2018, 1:56 PM
92 points
23 comments1 min readLW link

Embed­ded Curiosities

Scott Garrabrant and abramdemski
Nov 8, 2018, 2:19 PM
91 points
1 comment2 min readLW link

Sam Har­ris and the Is–Ought Gap

Tyrrell_McAllisterNov 16, 2018, 1:04 AM
91 points
46 comments6 min readLW link

“Just Suffer Un­til It Passes”

lionhearted (Sebastian Marshall)Feb 12, 2018, 4:01 AM
90 points
26 comments1 min readLW link

Dou­ble-Dip­ping in Dun­ning—Kruger

isovectorNov 28, 2018, 3:40 AM
88 points
32 comments3 min readLW link

Ex­pected Pain Parameters

AlicornJul 14, 2018, 7:30 PM
87 points
12 comments2 min readLW link

Bayesian Prob­a­bil­ity is for things that are Space-like Separated from You

Scott GarrabrantJul 10, 2018, 11:47 PM
87 points
22 comments2 min readLW link

In­tro­duc­ing the AI Align­ment Fo­rum (FAQ)

habryka, Ben Pace, Raemon and jimrandomh
Oct 29, 2018, 9:07 PM
87 points
8 comments6 min readLW link

The Un­rea­son­able Effec­tive­ness of Deep Learning

Richard_NgoSep 30, 2018, 3:48 PM
86 points
5 comments13 min readLW link
(thinkingcomplete.blogspot.com)

Sources of in­tu­itions and data on AGI

Scott GarrabrantJan 31, 2018, 11:30 PM
86 points
27 comments3 min readLW link

Wire­head your Chickens

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

Public Po­si­tions and Pri­vate Guts

VaniverOct 11, 2018, 7:38 PM
85 points
13 comments8 min readLW link

Coun­ter­in­tu­itive Com­par­a­tive Advantage

Wei DaiNov 28, 2018, 8:33 PM
85 points
8 comments2 min readLW link

Nyoom

AlicornOct 12, 2018, 2:34 AM
84 points
20 comments5 min readLW link

New edi­tion of “Ra­tion­al­ity: From AI to Zom­bies”

Rob BensingerDec 15, 2018, 9:33 PM
84 points
27 comments2 min readLW link

In­con­ve­nience Is Qual­i­ta­tively Bad

AlicornFeb 26, 2018, 11:27 PM
83 points
52 comments2 min readLW link

The fun­nel of hu­man experience

eukaryoteOct 10, 2018, 2:46 AM
83 points
31 comments3 min readLW link1 review
(eukaryotewritesblog.com)

Open ques­tion: are min­i­mal cir­cuits dae­mon-free?

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

Pre­dic­tion Mar­kets Are About Be­ing Right

ZviDec 8, 2018, 2:00 PM
83 points
7 comments7 min readLW link
(thezvi.wordpress.com)

How to Build a Lumenator

RaemonAug 12, 2018, 5:11 AM
82 points
27 comments2 min readLW link

Fast­ing Mimick­ing Diet Looks Pretty Good

sarahconstantin4 Oct 2018 19:50 UTC
81 points
4 comments3 min readLW link
(srconstantin.wordpress.com)

Meta-tations on Moder­a­tion: Towards Public Archipelago

Raemon25 Feb 2018 3:59 UTC
81 points
176 comments23 min readLW link

An­nounce­ment: AI al­ign­ment prize win­ners and next round

cousin_it15 Jan 2018 14:33 UTC
81 points
68 comments2 min readLW link

When is un­al­igned AI morally valuable?

paulfchristiano25 May 2018 1:57 UTC
81 points
53 comments10 min readLW link

(A → B) → A

Scott Garrabrant11 Sep 2018 22:38 UTC
80 points
11 comments2 min readLW link

Prob­a­bil­ity is Real, and Value is Complex

abramdemski20 Jul 2018 5:24 UTC
80 points
21 comments6 min readLW link

The Case Against Education

Zvi15 Apr 2018 12:30 UTC
79 points
44 comments7 min readLW link
(thezvi.wordpress.com)

In­tro­duc­ing the Longevity Re­search Institute

sarahconstantin14 Dec 2018 20:20 UTC
79 points
11 comments1 min readLW link
(srconstantin.wordpress.com)

Mark Eichen­laub: How to de­velop sci­en­tific intuition

Kaj_Sotala23 Oct 2018 13:30 UTC
78 points
6 comments8 min readLW link
(kajsotala.fi)

How to par­ent more predictably

jefftk10 Jul 2018 15:18 UTC
78 points
1 comment4 min readLW link

Recom­men­da­tions vs. Guidelines

Scott Alexander13 Apr 2018 4:10 UTC
77 points
18 comments5 min readLW link
(slatestarcodex.com)

Give praise

null29 Apr 2018 21:00 UTC
77 points
87 comments1 min readLW link1 review

Swim­ming Up­stream: A Case Study in In­stru­men­tal Rationality

TurnTrout3 Jun 2018 3:16 UTC
77 points
7 comments8 min readLW link

De­bate Rules In Ben­jamin Fran­klin’s Junto

namespace30 Oct 2018 23:42 UTC
77 points
8 comments1 min readLW link

Manda­tory Obsessions

Jacob Falkovich14 Nov 2018 18:19 UTC
77 points
14 comments6 min readLW link

What Are Mee­tups Ac­tu­ally Try­ing to Ac­com­plish?

mingyuan8 Feb 2018 5:30 UTC
77 points
17 comments12 min readLW link

More Babble

alkjash12 Jan 2018 1:41 UTC
76 points
24 comments8 min readLW link
(radimentary.wordpress.com)

Why it took so long to do the Fermi calcu­la­tion right?

Jan_Kulveit2 Jul 2018 20:29 UTC
76 points
20 comments1 min readLW link

Prune

alkjash12 Jan 2018 22:50 UTC
76 points
11 comments4 min readLW link
(radimentary.wordpress.com)

Track-Back Meditation

abramdemski11 Sep 2018 10:31 UTC
76 points
19 comments7 min readLW link

Paper Trauma

Qiaochu_Yuan31 Jan 2018 22:05 UTC
76 points
63 comments1 min readLW link

De­mon Threads

Raemon7 Jan 2018 3:48 UTC
76 points
74 comments9 min readLW link

Ar­gue Poli­tics* With Your Best Friends

sarahconstantin15 Dec 2018 19:00 UTC
75 points
6 comments6 min readLW link
(srconstantin.wordpress.com)