Mul­ti­vari­ate es­ti­ma­tion & the Squig­gly language

ozziegooenSep 5, 2020, 4:35 AM
44 points
5 comments7 min readLW link

How Much Com­pu­ta­tional Power Does It Take to Match the Hu­man Brain?

habrykaSep 12, 2020, 6:38 AM
44 points
1 comment1 min readLW link
(www.openphilanthropy.org)

Petrov Event Roundup 2020

RaemonSep 24, 2020, 9:07 PM
43 points
0 comments1 min readLW link

Ex­pan­sive trans­la­tions: con­sid­er­a­tions and possibilities

ozziegooenSep 18, 2020, 3:39 PM
43 points
15 comments6 min readLW link

[Question] Fore­cast­ing Thread: Ex­is­ten­tial Risk

AmandangoSep 22, 2020, 3:44 AM
43 points
39 comments2 min readLW link

The Box Spread Trick: Get rich slightly faster

Thomas KwaSep 1, 2020, 9:41 PM
43 points
44 comments6 min readLW link

Ice

SlimepriestessSep 6, 2020, 6:30 PM
42 points
1 comment6 min readLW link
(hivewired.wordpress.com)

Gems from the Wiki: Acausal Trade

Sep 13, 2020, 12:23 AM
42 points
8 comments7 min readLW link
(www.lesswrong.com)

Ra­tion­al­ity and playfulness

DirectedEvolutionSep 12, 2020, 5:14 AM
42 points
1 comment11 min readLW link

Hu­man Bi­ases that Ob­scure AI Progress

Danielle EnsignSep 25, 2020, 12:24 AM
42 points
2 comments4 min readLW link

CTWTB: Paths of Com­pu­ta­tion State

johnswentworthSep 8, 2020, 8:44 PM
41 points
1 comment4 min readLW link

What Does “Sig­nal­ling” Mean?

abramdemskiSep 16, 2020, 9:19 PM
38 points
18 comments3 min readLW link

[Question] Why is Bayesi­anism im­por­tant for ra­tio­nal­ity?

Chris_LeongSep 1, 2020, 4:24 AM
37 points
24 comments1 min readLW link

[Question] What’s the best overview of com­mon Micro­morts?

RaemonSep 3, 2020, 2:39 AM
37 points
8 comments1 min readLW link1 review

Zen and Ra­tion­al­ity: Just This Is It

Gordon Seidoh WorleySep 20, 2020, 10:31 PM
36 points
6 comments2 min readLW link1 review

Sur­viv­ing Petrov Day

Mati_RoySep 26, 2020, 4:40 PM
35 points
8 comments2 min readLW link

Not all com­mu­ni­ca­tion is ma­nipu­la­tion: Chap­er­ones don’t ma­nipu­late proteins

ChristianKlSep 27, 2020, 4:45 PM
35 points
14 comments2 min readLW link

Sun­day Septem­ber 6, 12pm (PT) — Ca­sual hang­ing out with the LessWrong community

habrykaSep 3, 2020, 2:08 AM
34 points
10 comments1 min readLW link

I’m Vot­ing For Ranked Choice, But I Don’t Like It

jefftkSep 20, 2020, 6:40 PM
32 points
12 comments1 min readLW link
(www.jefftk.com)

A case study in simu­lacra lev­els and the Four Chil­dren of the Seder

DirectedEvolutionSep 14, 2020, 10:31 PM
32 points
1 comment4 min readLW link

On Nice­ness: Look­ing for Pos­i­tive Externalities

Neel NandaSep 14, 2020, 6:03 PM
32 points
0 comments10 min readLW link
(www.neelnanda.io)

Safety via se­lec­tion for obedience

Richard_NgoSep 10, 2020, 10:04 AM
31 points
1 comment5 min readLW link

Hello or­di­nary folks, I’m the Cho­sen One

dadadarrenSep 4, 2020, 7:59 PM
31 points
3 comments3 min readLW link

Gems from the Wiki: Para­noid Debating

Sep 15, 2020, 3:51 AM
30 points
1 comment3 min readLW link
(www.lesswrong.com)

The “Backchain­ing to Lo­cal Search” Tech­nique in AI Alignment

adamShimiSep 18, 2020, 3:05 PM
29 points
1 comment2 min readLW link

An­thropic Rea­son­ing and Per­spec­tive-Based Ar­gu­ments

dadadarrenSep 1, 2020, 12:36 PM
28 points
59 comments2 min readLW link

EA Re­la­tion­ship Status

jefftkSep 19, 2020, 1:50 AM
28 points
16 comments1 min readLW link
(www.jefftk.com)

[AN #117]: How neu­ral nets would fare un­der the TEVV framework

Rohin ShahSep 16, 2020, 5:20 PM
27 points
0 comments7 min readLW link
(mailchi.mp)

[Question] Where is hu­man level on text pre­dic­tion? (GPTs task)

Daniel KokotajloSep 20, 2020, 9:00 AM
27 points
19 comments1 min readLW link

Me­moriz­ing a Deck of Cards

ToflySep 16, 2020, 1:31 AM
27 points
1 comment2 min readLW link

Do­ing dis­course bet­ter: Stuff I wish I knew

dynomightSep 29, 2020, 2:34 PM
27 points
11 comments1 min readLW link
(dyno-might.github.io)

Spoiler-Free Re­view: The Stan­ley Parable

ZviSep 24, 2020, 2:40 PM
27 points
4 comments1 min readLW link
(thezvi.wordpress.com)

Distributed pub­lic goods provision

paulfchristianoSep 26, 2020, 9:20 PM
27 points
3 comments5 min readLW link
(sideways-view.com)

‘Ugh fields’, or why you can’t even bear to think about that task (Rob Wiblin)

habrykaSep 11, 2020, 8:31 PM
26 points
17 comments2 min readLW link
(medium.com)

Indig­na­tion in re­sponse to the 1890 census

jasoncrawfordSep 8, 2020, 8:14 PM
26 points
1 comment1 min readLW link
(rootsofprogress.org)

Sun­day Septem­ber 20, 12:00PM (PT) — talks by Eric Rogstad, Daniel Koko­ta­jlo and more

habrykaSep 17, 2020, 12:27 AM
26 points
8 comments1 min readLW link

Safer sand­box­ing via col­lec­tive separation

Richard_NgoSep 9, 2020, 7:49 PM
26 points
6 comments4 min readLW link

Vi­su­al­iz­ing the text­book for fun and profit

DirectedEvolutionSep 24, 2020, 7:37 PM
26 points
4 comments6 min readLW link

on “learn­ing to sum­ma­rize”

nostalgebraistSep 12, 2020, 3:20 AM
25 points
13 comments8 min readLW link
(nostalgebraist.tumblr.com)

[Question] If there were an in­ter­ac­tive soft­ware teach­ing Yud­kowskian ra­tio­nal­ity, what con­cepts would you want to see it teach?

MikkWSep 2, 2020, 5:37 AM
25 points
20 comments1 min readLW link

Es­ca­la­tion Out­side the System

jefftkSep 8, 2020, 6:20 PM
25 points
11 comments2 min readLW link
(www.jefftk.com)

Note­book for gen­er­at­ing fore­cast­ing bets

AmandangoSep 26, 2020, 8:36 PM
25 points
0 comments1 min readLW link

Petrov Day is not about unilat­eral action

senSep 26, 2020, 1:41 PM
25 points
0 comments1 min readLW link

Au­gust 2020 gw­ern.net newsletter

gwernSep 1, 2020, 9:04 PM
25 points
4 commentsLW link
(www.gwern.net)

[Question] Egan’s The­o­rem?

johnswentworthSep 13, 2020, 5:47 PM
24 points
13 comments1 min readLW link

Should some var­i­ant of longter­mism iden­tify as a re­li­gion?

mako yassSep 11, 2020, 5:02 AM
23 points
8 comments2 min readLW link

Rus­sian x-risks newslet­ter Sum­mer 2020

avturchinSep 1, 2020, 2:06 PM
22 points
6 comments1 min readLW link

[Link] Five Years and One Week of Less Wrong

abramdemskiSep 14, 2020, 4:49 PM
22 points
2 comments2 min readLW link
(slatestarcodex.com)

AI Ad­van­tages [Gems from the Wiki]

Sep 22, 2020, 10:44 PM
22 points
7 comments2 min readLW link
(www.lesswrong.com)

Luna First, But Not To Live There

NathanielMRouthSep 8, 2020, 3:14 AM
21 points
21 comments5 min readLW link
(nathanielmrouth.wordpress.com)