[Question] How to deal with a mis­lead­ing con­fer­ence talk about AI risk?

rmoehnJun 27, 2019, 9:04 PM
21 points
12 comments4 min readLW link

[Question] Is it good prac­tice to write ques­tions/​com­ments on old posts you’re try­ing to un­der­stand?

Liam DonovanJun 27, 2019, 9:23 AM
22 points
5 comments1 min readLW link

[Question] What are prin­ci­pled ways for pe­nal­is­ing com­plex­ity in prac­tice?

BuckyJun 27, 2019, 7:28 AM
36 points
12 comments1 min readLW link

Embed­ded Agency: Not Just an AI Problem

johnswentworthJun 27, 2019, 12:35 AM
15 points
10 comments2 min readLW link

Jor­dan Peter­son on AI-FOOM

Bound_upJun 26, 2019, 5:05 PM
3 points
7 comments1 min readLW link

Apoca­lypse, corrupted

Stuart_ArmstrongJun 26, 2019, 1:46 PM
20 points
13 comments2 min readLW link

[Question] What does the word “col­lab­o­ra­tive” mean in the phrase “col­lab­o­ra­tive truth­seek­ing”?

Zack_M_DavisJun 26, 2019, 5:26 AM
27 points
23 comments1 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)

Writ­ing chil­dren’s pic­ture books

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

[Question] Only op­ti­mize to 95 %

Leo ShineJun 25, 2019, 8:50 PM
7 points
9 comments1 min readLW link

Re­search Agenda in re­verse: what *would* a solu­tion look like?

Stuart_ArmstrongJun 25, 2019, 1:52 PM
35 points
25 comments1 min readLW link

Ar­bital Scrape V2

emmabJun 25, 2019, 10:03 AM
40 points
6 comments1 min readLW link

[Question] What’s up with self-es­teem?

abramdemskiJun 25, 2019, 3:38 AM
39 points
14 comments2 min readLW link

Pitts­burgh SSC/​RAT-ad­ja­cent meetup

fr8trainJun 25, 2019, 2:11 AM
1 point
0 comments1 min readLW link

Causal Real­ity vs So­cial Reality

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

Ma­chine Learn­ing Pro­jects on IDA

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

Be­ing the (Pareto) Best in the World

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

[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)

Ex­plain­ing “The Crack­pot Bet”

glennonymousJun 24, 2019, 3:17 PM
−40 points
20 comments3 min readLW link

How does one get in­vited to the al­ign­ment fo­rum?

Chris_LeongJun 23, 2019, 9:39 AM
15 points
5 comments1 min readLW link

Pod­cast—Pu­tanu­monit on The Switch

Jacob FalkovichJun 23, 2019, 4:09 AM
6 points
2 comments1 min readLW link

The Foun­da­tional Toolbox for Life: Introduction

ExCephJun 22, 2019, 6:11 AM
23 points
2 comments6 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

The Hacker Learns to Trust

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

“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)

De­ci­sions are hard, words feel easier

HazardJun 21, 2019, 4:17 PM
9 points
4 comments2 min readLW link

Split­ting Concepts

HazardJun 21, 2019, 4:03 PM
8 points
0 comments2 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)

Is your un­cer­tainty re­solv­able?

RaemonJun 21, 2019, 7:32 AM
30 points
15 comments1 min readLW link

Should ra­tio­nal­ity be a move­ment?

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

Let Values Drift

Gordon Seidoh WorleyJun 20, 2019, 8:45 PM
4 points
19 comments8 min readLW link

A case for strat­egy re­search: what it is and why we need more of it

SiebeJun 20, 2019, 8:22 PM
24 points
19 comments20 min readLW link

[Question] LW Dev ques­tion: FB-style tag­ging?

Dr_ManhattanJun 20, 2019, 7:19 PM
11 points
1 comment1 min readLW link

STRUCTURE: A Hazardous Guide to Words

HazardJun 20, 2019, 3:27 PM
8 points
7 comments5 min readLW link

Should there be a header fea­ture?

Chris_LeongJun 20, 2019, 6:45 AM
2 points
2 comments1 min readLW link

Defend­ing points you don’t care about

HazardJun 19, 2019, 8:40 PM
41 points
6 comments4 min readLW link

Words Aren’t Type Safe

HazardJun 19, 2019, 8:34 PM
22 points
12 comments3 min readLW link

Ar­gu­ing Definitions

HazardJun 19, 2019, 8:29 PM
12 points
1 comment4 min readLW link

LW2.0: Tech­nol­ogy Plat­form for In­tel­lec­tual Progress

RubyJun 19, 2019, 8:25 PM
31 points
5 comments7 min readLW link

LW2.0: Com­mu­nity, Cul­ture, and In­tel­lec­tual Progress

RubyJun 19, 2019, 8:25 PM
27 points
2 comments6 min readLW link

1hr talk: In­tro to AGI safety

Steven ByrnesJun 18, 2019, 9:41 PM
36 points
4 comments24 min readLW link

Reneg­ing proso­cially by Dun­can Sabien

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

Magic Arena Bot Drafting

ZviJun 18, 2019, 4:00 PM
18 points
1 comment18 min readLW link
(thezvi.wordpress.com)

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

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

Rea­son isn’t magic

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

Dis­cus­sion Thread: The AI Does Not Hate You by Tom Chivers

RubyJun 17, 2019, 11:43 PM
26 points
10 comments1 min readLW link

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

Prefer­ence con­di­tional on cir­cum­stances and past prefer­ence satisfaction

Stuart_ArmstrongJun 17, 2019, 3:30 PM
11 points
1 comment1 min readLW link

[Question] In phys­i­cal es­cha­tol­ogy, is Aes­ti­va­tion a sound strat­egy?

mako yassJun 17, 2019, 7:27 AM
17 points
11 comments1 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