Be­ing the (Pareto) Best in the World

johnswentworthJun 24, 2019, 6:36 PM
474 points
60 comments3 min readLW link3 reviews

Wel­come to LessWrong!

Jun 14, 2019, 7:42 PM
464 points
65 comments2 min readLW link

Mis­takes with Con­ser­va­tion of Ex­pected Evidence

abramdemskiJun 8, 2019, 11:07 PM
232 points
29 comments12 min readLW link1 review

Steel­man­ning Divination

VaniverJun 5, 2019, 10:53 PM
206 points
49 comments6 min readLW link2 reviews

Selec­tion vs Control

abramdemskiJun 2, 2019, 7:01 AM
175 points
26 comments11 min readLW link2 reviews

The Schel­ling Choice is “Rab­bit”, not “Stag”

RaemonJun 8, 2019, 12:24 AM
165 points
52 comments12 min readLW link3 reviews

Book Re­view: The Se­cret Of Our Success

Scott AlexanderJun 5, 2019, 6:50 AM
164 points
20 comments25 min readLW link2 reviews
(slatestarcodex.com)

Rea­son isn’t magic

BenquoJun 18, 2019, 4:04 AM
161 points
19 comments2 min readLW link3 reviews
(benjaminrosshoffman.com)

Writ­ing chil­dren’s pic­ture books

jessicataJun 25, 2019, 9:43 PM
125 points
22 comments5 min readLW link
(unstableontology.com)

De­cep­tive Alignment

Jun 5, 2019, 8:16 PM
118 points
20 comments17 min readLW link

The In­ner Align­ment Problem

Jun 4, 2019, 1:20 AM
105 points
17 comments13 min readLW link

LessWrong FAQ

RubyJun 14, 2019, 7:03 PM
91 points
55 comments25 min readLW link

Ar­bital scrape

emmabJun 6, 2019, 11:11 PM
89 points
23 comments1 min readLW link

Tal Yarkoni: No, it’s not The In­cen­tives—it’s you

Zack_M_DavisJun 11, 2019, 7:09 AM
89 points
119 comments1 min readLW link4 reviews
(www.talyarkoni.org)

Cir­cle Games

sarahconstantinJun 6, 2019, 4:40 PM
85 points
15 comments4 min readLW link1 review
(srconstantin.wordpress.com)

Con­di­tions for Mesa-Optimization

Jun 1, 2019, 8:52 PM
84 points
48 comments12 min readLW link

Risks from Learned Op­ti­miza­tion: Con­clu­sion and Re­lated Work

Jun 7, 2019, 7:53 PM
82 points
5 comments6 min readLW link

Epistemic Spot Check: The Role of De­liber­ate Prac­tice in the Ac­qui­si­tion of Ex­pert Performance

ElizabethJun 25, 2019, 11:00 PM
81 points
9 comments4 min readLW link
(acesounderglass.com)

The Hacker Learns to Trust

Ben PaceJun 22, 2019, 12:27 AM
80 points
18 comments8 min readLW link
(medium.com)

Rea­son­able Explanations

AlicornJun 16, 2019, 5:29 AM
78 points
7 comments1 min readLW link

FB/​Dis­cord Style Reacts

RaemonJun 1, 2019, 9:34 PM
77 points
95 comments5 min readLW link

Mo­ral Mazes and Short Termism

ZviJun 2, 2019, 11:30 AM
74 points
21 comments4 min readLW link
(thezvi.wordpress.com)

Reneg­ing proso­cially by Dun­can Sabien

philip_bJun 18, 2019, 6:52 PM
70 points
5 comments1 min readLW link
(medium.com)

Re­search Agenda v0.9: Syn­the­sis­ing a hu­man’s prefer­ences into a util­ity function

Stuart_ArmstrongJun 17, 2019, 5:46 PM
70 points
26 comments33 min readLW link

Con­cep­tual Prob­lems with UDT and Policy Selection

abramdemskiJun 28, 2019, 11:50 PM
66 points
16 comments9 min readLW link

AGI will dras­ti­cally in­crease economies of scale

Wei DaiJun 7, 2019, 11:17 PM
65 points
26 comments1 min readLW link

Recom­men­da­tion Fea­tures on LessWrong

Jun 15, 2019, 12:23 AM
62 points
36 comments4 min readLW link

Book Re­view: Why Are The Prices So Damn High?

sarahconstantinJun 28, 2019, 7:40 PM
61 points
7 comments8 min readLW link
(srconstantin.wordpress.com)

The LessWrong Team

RubyJun 1, 2019, 12:43 AM
61 points
8 comments3 min readLW link

[Question] What is the ev­i­dence for pro­duc­tivity benefits of weightlift­ing?

jpJun 2, 2019, 7:17 PM
59 points
27 comments1 min readLW link

In­stead of “I’m anx­ious,” try “I feel threat­ened”

Holly_ElmoreJun 28, 2019, 5:24 AM
58 points
19 comments2 min readLW link
(mhollyelmoreblog.wordpress.com)

[AN #58] Mesa op­ti­miza­tion: what it is, and why we should care

Rohin ShahJun 24, 2019, 4:10 PM
55 points
10 comments8 min readLW link
(mailchi.mp)

“But It Doesn’t Mat­ter”

Zack_M_DavisJun 1, 2019, 2:06 AM
55 points
17 comments1 min readLW link

GreaterWrong Ar­bital Viewer

clone of saturnJun 28, 2019, 6:32 AM
55 points
9 comments1 min readLW link
(arbital.greaterwrong.com)

Some Ways Co­or­di­na­tion is Hard

ZviJun 13, 2019, 1:00 PM
55 points
11 comments10 min readLW link1 review
(thezvi.wordpress.com)

Align­ing a toy model of optimization

paulfchristianoJun 28, 2019, 8:23 PM
53 points
25 comments3 min readLW link

“The Bit­ter Les­son”, an ar­ti­cle about com­pute vs hu­man knowl­edge in AI

the gears to ascensionJun 21, 2019, 5:24 PM
52 points
14 comments4 min readLW link
(www.incompleteideas.net)

Pa­ter­nal Formats

abramdemskiJun 9, 2019, 1:26 AM
52 points
35 comments2 min readLW link

Ma­chine Learn­ing Pro­jects on IDA

Jun 24, 2019, 6:38 PM
49 points
3 comments2 min readLW link

Does Bayes Beat Good­hart?

abramdemskiJun 3, 2019, 2:31 AM
48 points
26 comments7 min readLW link

[Question] Is there a guide to ‘Prob­lems that are too fast to Google’?

VaniverJun 17, 2019, 5:04 AM
48 points
13 comments1 min readLW link

Should ra­tio­nal­ity be a move­ment?

Chris_LeongJun 20, 2019, 11:09 PM
48 points
13 comments3 min readLW link

How hard is it for al­tru­ists to dis­cuss go­ing against bad equil­ibria?

abramdemskiJun 22, 2019, 3:42 AM
46 points
6 comments11 min readLW link

Causal Real­ity vs So­cial Reality

RubyJun 24, 2019, 11:50 PM
46 points
96 comments6 min readLW link

Let’s talk about “Con­ver­gent Ra­tion­al­ity”

David Scott Krueger (formerly: capybaralet)Jun 12, 2019, 9:53 PM
44 points
33 comments6 min readLW link

On alien science

Richard_NgoJun 2, 2019, 2:50 PM
44 points
8 comments5 min readLW link
(thinkingcomplete.blogspot.com)

[Question] Do chil­dren lose ‘childlike cu­ri­os­ity?’ Why?

RaemonJun 29, 2019, 10:42 PM
44 points
15 comments1 min readLW link

On pointless waiting

Kaj_SotalaJun 10, 2019, 8:58 AM
43 points
6 comments1 min readLW link

[Question] Is the “busi­ness cy­cle” an ac­tual eco­nomic prin­ci­ple?

LironJun 18, 2019, 2:52 PM
43 points
15 comments1 min readLW link

Model­ing AGI Safety Frame­works with Causal In­fluence Diagrams

Ramana KumarJun 21, 2019, 12:50 PM
43 points
6 comments1 min readLW link
(arxiv.org)