At­tri­bu­tions, Karma and bet­ter dis­cov­er­abil­ity for wiki/​tag features

2 Jun 2021 23:47 UTC
93 points
8 comments1 min readLW link

Thoughts on the Align­ment Im­pli­ca­tions of Scal­ing Lan­guage Models

leogao2 Jun 2021 21:32 UTC
82 points
11 comments17 min readLW link

[Question] What ques­tion would you like to col­lab­o­rate on?

weathersystems2 Jun 2021 19:31 UTC
12 points
12 comments2 min readLW link

Selec­tion Has A Qual­ity Ceiling

johnswentworth2 Jun 2021 18:25 UTC
144 points
18 comments4 min readLW link1 review

[Question] Can you im­prove your in­tel­li­gence with these types of ex­er­cises?

icompetetowin1 Jun 2021 21:13 UTC
2 points
9 comments1 min readLW link

“Ex­is­ten­tial risk from AI” sur­vey results

Rob Bensinger1 Jun 2021 20:02 UTC
65 points
7 comments11 min readLW link

If You Want to Find Truth You Need to Step Into Cringe

Writer1 Jun 2021 19:03 UTC
23 points
12 comments5 min readLW link
(youtu.be)

Power dy­nam­ics as a blind spot or blurry spot in our col­lec­tive world-mod­el­ing, es­pe­cially around AI

Andrew_Critch1 Jun 2021 18:45 UTC
182 points
26 comments6 min readLW link

Fore­cast­ing Newslet­ter: May 2021

NunoSempere1 Jun 2021 15:51 UTC
11 points
2 comments11 min readLW link

Rus­sian x-risks newslet­ter spring 21

avturchin1 Jun 2021 12:10 UTC
19 points
2 comments1 min readLW link

Which an­i­mals can suffer?

Just Learning1 Jun 2021 3:42 UTC
7 points
16 comments1 min readLW link

Strength, not courage, is the sec­ond com­po­nent of goodness

Srdjan Miletic1 Jun 2021 3:32 UTC
4 points
5 comments2 min readLW link

[Question] Which ac­tivi­ties do you pre­fer to bet­ter re­cover pro­duc­tivity?

Just Learning1 Jun 2021 1:01 UTC
9 points
5 comments1 min readLW link

Net­works of Trust vs Markets

Henrik Karlsson31 May 2021 19:59 UTC
106 points
23 comments5 min readLW link

[Question] What is the Risk of Long Covid af­ter Vac­ci­na­tion?

dawangy31 May 2021 19:32 UTC
64 points
15 comments1 min readLW link

Zen and Ra­tion­al­ity: Con­tin­u­ous Practice

Gordon Seidoh Worley31 May 2021 18:42 UTC
14 points
1 comment1 min readLW link

[Question] How do you con­duct a per­sonal study re­treat?

Aay17ush31 May 2021 14:25 UTC
1 point
0 comments1 min readLW link

Anatomy, dis­eases and ag­ing damage

ChristianKl31 May 2021 14:01 UTC
24 points
6 comments4 min readLW link

TEAM: a dra­mat­i­cally im­proved form of therapy

Jakob_J31 May 2021 13:33 UTC
28 points
20 comments4 min readLW link

Up­date 2021-05-31

jefftk31 May 2021 13:30 UTC
2 points
5 comments1 min readLW link
(www.jefftk.com)

Po­modoros worked dur­ing a day: an anal­y­sis of Alex’s data

Derek M. Jones31 May 2021 13:27 UTC
5 points
0 comments3 min readLW link
(shape-of-code.coding-guidelines.com)

On mak­ing fic­tional mir­a­cles seem plausible

Yair Halberstadt31 May 2021 11:32 UTC
5 points
4 comments3 min readLW link

For Bet­ter Com­ment­ing, Take an Oath of Re­ply.

DirectedEvolution31 May 2021 6:01 UTC
42 points
17 comments2 min readLW link

Mega Links Post for Mar-Apr-May 2021

ike31 May 2021 3:47 UTC
13 points
0 comments12 min readLW link
(misinfounderload.substack.com)

The Cost of Con­ve­nience.…

njv31 May 2021 0:49 UTC
−14 points
3 comments6 min readLW link

In­tro­duc­ing Ra­tional Animations

Writer31 May 2021 0:49 UTC
17 points
4 comments2 min readLW link

Why don’t long run­ning con­ver­sa­tions hap­pen on LessWrong?

Adam Zerner30 May 2021 22:36 UTC
64 points
75 comments2 min readLW link

Paper Re­view: Math­e­mat­i­cal Truth

Alex Hollow30 May 2021 20:25 UTC
5 points
14 comments3 min readLW link
(alexhollow.wordpress.com)

How count­ing neu­trons ex­plains nu­clear waste

jasoncrawford30 May 2021 18:10 UTC
100 points
11 comments14 min readLW link
(rootsofprogress.org)

Elec­tric heat pumps (Mini-Splits) vs Nat­u­ral gas boilers

Steven Byrnes30 May 2021 15:51 UTC
16 points
13 comments3 min readLW link

What is the most effec­tive way to donate to AGI XRisk miti­ga­tion?

JoshuaFox30 May 2021 11:08 UTC
44 points
11 comments1 min readLW link

Seat­tle Robot Cult

lsusr29 May 2021 23:54 UTC
18 points
2 comments1 min readLW link

[Question] Use of GPT-3 for iden­ti­fy­ing Phish­ing and other email based at­tacks?

jmh29 May 2021 17:11 UTC
6 points
1 comment1 min readLW link

[Event] Weekly Align­ment Re­search Coffee Time

adamShimi29 May 2021 13:26 UTC
12 points
5 comments1 min readLW link

How to Write Science Fic­tion and Fan­tasy—A Short Summary

Jsevillamol29 May 2021 11:47 UTC
26 points
4 comments4 min readLW link

Two Defi­ni­tions of Generalization

ozziegooen29 May 2021 4:20 UTC
33 points
4 comments2 min readLW link

The San­ity Water­line Bul­ges at the Middle

matejsuchy29 May 2021 3:15 UTC
−7 points
5 comments2 min readLW link
(matejsuchy.substack.com)

Against Be­ing Against Growth

Alex Hollow29 May 2021 2:18 UTC
−1 points
5 comments2 min readLW link
(alexhollow.wordpress.com)

Wrist Update

jefftk29 May 2021 1:30 UTC
12 points
11 comments1 min readLW link
(www.jefftk.com)

[Question] How one uses set the­ory for al­ign­ment prob­lem?

Just Learning29 May 2021 0:28 UTC
8 points
6 comments1 min readLW link

[Question] Is any­one else frus­trated with ‘un-in­for­ma­tive’ post ti­tles?

Kenny28 May 2021 20:11 UTC
18 points
10 comments1 min readLW link

Teach­ing ML to an­swer ques­tions hon­estly in­stead of pre­dict­ing hu­man answers

paulfchristiano28 May 2021 17:30 UTC
53 points
18 comments16 min readLW link
(ai-alignment.com)

The blue-min­imis­ing robot and model splintering

Stuart_Armstrong28 May 2021 15:09 UTC
13 points
4 comments3 min readLW link1 review

Cu­rated con­ver­sa­tions with brilli­ant rationalists

spencerg28 May 2021 14:23 UTC
153 points
18 comments6 min readLW link

(Try­ing To) Study Text­books Effec­tively: A Year of Experimentation

DirectedEvolution28 May 2021 5:51 UTC
67 points
13 comments5 min readLW link

Why Prefetch Is Broken

jefftk28 May 2021 2:20 UTC
13 points
7 comments2 min readLW link
(www.jefftk.com)

[Question] Aphantasia

Crackatook28 May 2021 1:55 UTC
7 points
23 comments1 min readLW link

Pre­dict re­sponses to the “ex­is­ten­tial risk from AI” survey

Rob Bensinger28 May 2021 1:32 UTC
44 points
6 comments2 min readLW link

AXRP Epi­sode 7.5 - Fore­cast­ing Trans­for­ma­tive AI from Biolog­i­cal An­chors with Ajeya Cotra

DanielFilan28 May 2021 0:20 UTC
24 points
1 comment67 min readLW link

The Ho­muncu­lus Problem

abramdemski27 May 2021 20:25 UTC
44 points
38 comments5 min readLW link