New Speaker Series on AI Align­ment Start­ing March 3

Zechen ZhangFeb 26, 2022, 7:31 PM
7 points
1 comment1 min readLW link

[Linkpost] Re­view: Happiness

VipulNaikFeb 26, 2022, 5:10 PM
6 points
0 comments1 min readLW link

Am­bi­guity causes conflict

Ege ErdilFeb 26, 2022, 4:53 PM
24 points
9 comments8 min readLW link

How do new mod­els from OpenAI, Deep­Mind and An­thropic perform on Truth­fulQA?

Owain_EvansFeb 26, 2022, 12:46 PM
44 points
3 comments11 min readLW link

IMO challenge bet with Eliezer

paulfchristianoFeb 26, 2022, 4:50 AM
179 points
26 comments3 min readLW link

Bet­ter a Brave New World than a dead one

YitzFeb 25, 2022, 11:11 PM
9 points
5 comments4 min readLW link

My at­ti­tude to­wards death

Richard_NgoFeb 25, 2022, 3:20 PM
63 points
31 comments6 min readLW link
(thinkingcomplete.blogspot.com)

Trust-max­i­miz­ing AGI

Feb 25, 2022, 3:13 PM
7 points
26 comments9 min readLW link
(universalprior.substack.com)

[Question] Why would GDP X GDP Per Cap­ita be used as a mea­sure­ment of power? What’s the pur­pose of squar­ing GDP?

dqups1Feb 25, 2022, 2:56 AM
1 point
5 comments1 min readLW link

The Big Pic­ture Of Align­ment (Talk Part 2)

johnswentworthFeb 25, 2022, 2:53 AM
34 points
12 comments1 min readLW link
(www.youtube.com)

[Question] How do I Op­ti­mize Team-Match­ing at Google

Carson DenisonFeb 24, 2022, 10:10 PM
8 points
1 comment1 min readLW link

Ar­tifi­cial Wordcels

Jacob FalkovichFeb 24, 2022, 9:18 PM
18 points
3 comments10 min readLW link

Cryptoepistemology

davidadFeb 24, 2022, 8:34 PM
31 points
3 comments2 min readLW link

Naturalism

LoganStrohlFeb 24, 2022, 7:45 PM
90 points
22 comments3 min readLW link

What would a thriv­ing progress move­ment look like?

jasoncrawfordFeb 24, 2022, 5:58 PM
18 points
7 comments2 min readLW link
(rootsofprogress.org)

Cap­tur­ing Uncer­tainty in Pre­dic­tion Markets

hawkebiaFeb 24, 2022, 5:23 PM
2 points
7 comments2 min readLW link

Less Light­ning Links at Length #1

ZviFeb 24, 2022, 4:20 PM
26 points
7 comments24 min readLW link
(thezvi.wordpress.com)

[Question] What’s the eas­iest way to cur­rently gen­er­ate images with ma­chine learn­ing?

ChristianKlFeb 24, 2022, 3:20 PM
24 points
4 comments1 min readLW link

Covid 2/​24/​22: The Next War

ZviFeb 24, 2022, 2:30 PM
39 points
4 comments12 min readLW link
(thezvi.wordpress.com)

Rus­sia has In­vaded Ukraine

lsusrFeb 24, 2022, 7:52 AM
174 points
268 comments3 min readLW link

The root cause of the Russo-Ukrainian war (and the long term solu­tion)

Long tryFeb 24, 2022, 6:56 AM
−21 points
4 comments1 min readLW link

Trans­former in­duc­tive bi­ases & RASP

Vivek HebbarFeb 24, 2022, 12:42 AM
15 points
4 comments1 min readLW link
(proceedings.mlr.press)

A com­ment on Ajeya Co­tra’s draft re­port on AI timelines

Matthew BarnettFeb 24, 2022, 12:41 AM
74 points
13 comments7 min readLW link

Chris­ti­ano and Yud­kowsky on AI pre­dic­tions and hu­man intelligence

Eliezer YudkowskyFeb 23, 2022, 9:34 PM
70 points
35 comments42 min readLW link

[Question] Was the K-T event a Great Filter?

YorethFeb 23, 2022, 8:35 PM
26 points
2 comments2 min readLW link

Pa­tient Observation

LoganStrohlFeb 23, 2022, 7:31 PM
129 points
4 comments10 min readLW link1 review

More GPT-3 and sym­bol grounding

Stuart_ArmstrongFeb 23, 2022, 6:30 PM
21 points
7 comments3 min readLW link

Some Tech­ni­cal Prob­lems With Mea­sur­ing Hap­piness (and some solu­tions)

Alexander de VriesFeb 23, 2022, 3:02 PM
16 points
0 comments14 min readLW link

[In­tro to brain-like-AGI safety] 5. The “long-term pre­dic­tor”, and TD learning

Steven ByrnesFeb 23, 2022, 2:44 PM
54 points
27 comments20 min readLW link

Do, Then Think

George3d6Feb 23, 2022, 1:40 PM
55 points
9 comments5 min readLW link
(www.epistem.ink)

In­ter­view with Nec­tome CEO Robert McIn­tyre—Brain Preser­va­tion, Per­sonal Iden­tity, AGI, and More

JohnGreerFeb 23, 2022, 1:54 AM
20 points
0 comments6 min readLW link

[Beta Fea­ture] Google-Docs-like edit­ing for LessWrong posts

Feb 23, 2022, 1:52 AM
165 points
26 comments3 min readLW link

How satis­fied should you ex­pect to be with your part­ner?

VaniverFeb 22, 2022, 11:27 PM
102 points
7 comments3 min readLW link2 reviews

Bay Ra­tion­al­ists Field Day

SurvivalBiasFeb 22, 2022, 7:55 PM
3 points
0 comments1 min readLW link

D&D.SCP: Ano­ma­lous Ac­qui­si­tions Eval­u­a­tion & Ruleset

aphyerFeb 22, 2022, 6:19 PM
32 points
9 comments8 min readLW link

[Question] What’s the sta­tus of TDCS for im­prov­ing in­tel­li­gence?

FinalFormal2Feb 22, 2022, 5:27 PM
13 points
0 comments1 min readLW link

Learn­ing By Writing

HoldenKarnofskyFeb 22, 2022, 3:50 PM
151 points
25 comments10 min readLW link3 reviews
(www.cold-takes.com)

Harms and pos­si­bil­ities of schooling

TsviBTFeb 22, 2022, 7:48 AM
123 points
38 comments12 min readLW link1 review

But­terfly Ideas

ElizabethFeb 22, 2022, 7:40 AM
200 points
10 comments3 min readLW link2 reviews
(acesounderglass.com)

ELK Pro­posal: Think­ing Via A Hu­man Imitator

TurnTroutFeb 22, 2022, 1:52 AM
31 points
6 comments11 min readLW link

Re­ward Good Bets That Had Bad Outcomes

Neel NandaFeb 22, 2022, 12:25 AM
44 points
11 comments8 min readLW link

The Art and Science of In­tu­ition Pumping

adamShimiFeb 22, 2022, 12:18 AM
26 points
3 comments9 min readLW link

[Question] Do any AI al­ign­ment orgs hire re­motely?

RobertMFeb 21, 2022, 10:33 PM
24 points
11 comments2 min readLW link

Con­voy Crackdown

ZviFeb 21, 2022, 10:10 PM
92 points
21 comments14 min readLW link
(thezvi.wordpress.com)

Ngo and Yud­kowsky on sci­en­tific rea­son­ing and pivotal acts

Feb 21, 2022, 8:54 PM
67 points
14 comments35 min readLW link

Direct Observation

LoganStrohlFeb 21, 2022, 8:51 PM
43 points
7 comments4 min readLW link

Align­ment re­search exercises

Richard_NgoFeb 21, 2022, 8:24 PM
150 points
17 comments8 min readLW link

Sum­mary/​Re­view/​Quotes of “The WEIRDest Peo­ple in the World” by Joseph Henrich

TorelloFeb 21, 2022, 8:03 PM
4 points
0 comments1 min readLW link

Seek­ing mod­els of LW’s aver­sion to religion

Visible_IgnoranceFeb 21, 2022, 6:54 PM
24 points
52 comments7 min readLW link

Con­test for out­lin­ing rules for this con­test.

abramdemskiFeb 21, 2022, 6:44 PM
40 points
11 comments1 min readLW link