Deter­minis­tic Strate­gies Can Be Suboptimal

Robert Kennedy4 Mar 2022 21:09 UTC
4 points
11 comments1 min readLW link

Sacri­fice for the Big Crunch

Cerdon4 Mar 2022 21:05 UTC
1 point
6 comments2 min readLW link

Higher Risk of Nu­clear War

jefftk4 Mar 2022 18:10 UTC
21 points
28 comments1 min readLW link
(www.jefftk.com)

When should you re­lo­cate to miti­gate the risk of dy­ing in a nu­clear war?

Adam Zerner4 Mar 2022 10:34 UTC
55 points
27 comments14 min readLW link

You’d Want The Right Answer

ship_shlap4 Mar 2022 2:33 UTC
4 points
4 comments1 min readLW link

In­tro­duc­ing my­self: Henry Lie­ber­man, MIT CSAIL, why­cantwe.org

Henry A Lieberman3 Mar 2022 23:42 UTC
−2 points
9 comments1 min readLW link

Rec­og­niz­ing and Deal­ing with Nega­tive Au­to­matic Thoughts

shminux3 Mar 2022 20:41 UTC
28 points
10 comments3 min readLW link

AI Perfor­mance on Hu­man Tasks

Asher Ellis3 Mar 2022 20:13 UTC
58 points
3 comments21 min readLW link

PSA: if you are in Rus­sia, prob­a­bly move out ASAP

yagudin3 Mar 2022 20:01 UTC
90 points
22 comments1 min readLW link

A Warm Up Prob­lem for Yud­kowsky’s New Fiction

Robert Kennedy3 Mar 2022 15:25 UTC
14 points
42 comments1 min readLW link

Covid 3/​3/​2022: Move Along

Zvi3 Mar 2022 12:00 UTC
35 points
9 comments10 min readLW link
(thezvi.wordpress.com)

The Geo­met­ric Series of 1/​(d+1) is a Frac­tion in Base-d

lsusr3 Mar 2022 5:06 UTC
14 points
4 comments1 min readLW link

Un­der­stand­ing Eliezer’s “Any Fact Would Move Me in the Same Direc­tion”

lhc3 Mar 2022 4:30 UTC
7 points
3 comments3 min readLW link

[Question] Would (my­opic) gen­eral pub­lic good pro­duc­ers sig­nifi­cantly ac­cel­er­ate the de­vel­op­ment of AGI?

mako yass2 Mar 2022 23:47 UTC
25 points
10 comments1 min readLW link

The Agent

Ideopunk2 Mar 2022 22:43 UTC
17 points
0 comments1 min readLW link

March 2022 Wel­come & Open Thread

Ruby2 Mar 2022 19:00 UTC
15 points
57 comments1 min readLW link

The Wicked Prob­lem Experience

HoldenKarnofsky2 Mar 2022 17:50 UTC
124 points
6 comments9 min readLW link1 review
(www.cold-takes.com)

The Limits Of Medicine—Part 2 - Ho­mo­gene­ity Assumptions

George3d62 Mar 2022 16:45 UTC
15 points
3 comments8 min readLW link
(www.epistem.ink)

[In­tro to brain-like-AGI safety] 6. Big pic­ture of mo­ti­va­tion, de­ci­sion-mak­ing, and RL

Steven Byrnes2 Mar 2022 15:26 UTC
68 points
17 comments15 min readLW link

The Round Table Manifesto

Jonathan Moregård2 Mar 2022 11:42 UTC
4 points
0 comments1 min readLW link
(honestliving.substack.com)

Or­di­nary and un­or­di­nary de­ci­sion theory

JonasMoss2 Mar 2022 11:39 UTC
3 points
7 comments7 min readLW link

Sum­mit-Seek­ing as Distinct From Mountaineering

Sable2 Mar 2022 10:40 UTC
16 points
2 comments5 min readLW link

[Question] Can you help me find this book?

mukashi2 Mar 2022 10:19 UTC
4 points
3 comments1 min readLW link

Luna Love­g­ood and the Fidelius Curse—Part 9

lsusr2 Mar 2022 9:45 UTC
25 points
9 comments2 min readLW link

Ukraine Si­tu­a­tion Re­port 2022/​03/​01

lsusr2 Mar 2022 5:07 UTC
121 points
59 comments10 min readLW link

Mus­ings on the Speed Prior

evhub2 Mar 2022 4:04 UTC
29 points
4 comments10 min readLW link

[Question] Are our com­mu­nity grouphouses typ­i­cally rented, or owned?

mako yass2 Mar 2022 3:36 UTC
11 points
17 comments1 min readLW link

Have You Tried Hiring Peo­ple?

rank-biserial2 Mar 2022 2:06 UTC
185 points
117 comments8 min readLW link1 review

How to de­velop safe superintelligence

martillopart1 Mar 2022 21:57 UTC
−5 points
3 comments13 min readLW link

[Question] What are the causal­ity effects of an agents pres­ence in a re­in­force­ment learn­ing environment

Jonas Kgomo1 Mar 2022 21:57 UTC
0 points
2 comments1 min readLW link

[Question] What are some ways to do a PhD with­out an ed­u­ca­tional institution

Jonas Kgomo1 Mar 2022 21:57 UTC
−1 points
2 comments1 min readLW link

[Question] What are some low-cog­ni­tive -work­load tasks that can help im­prove the world?

Yitz1 Mar 2022 17:47 UTC
29 points
11 comments1 min readLW link

The Age of Over-pop­u­la­tion (Chap­ter 4)

Justin Bullock1 Mar 2022 14:10 UTC
6 points
0 comments10 min readLW link

[Link] Aligned AI AMA

Stuart_Armstrong1 Mar 2022 12:01 UTC
18 points
0 comments1 min readLW link

RFC WWIII

Adam Zerner1 Mar 2022 9:10 UTC
45 points
34 comments9 min readLW link

Seek Mis­takes in the Space Between Math and Reality

aphyer1 Mar 2022 5:58 UTC
29 points
23 comments4 min readLW link

Late 2021 MIRI Con­ver­sa­tions: AMA /​ Discussion

Rob Bensinger28 Feb 2022 20:03 UTC
119 points
199 comments1 min readLW link

Mun­dane, sharp, crazy

Nyeogmi28 Feb 2022 20:02 UTC
14 points
1 comment4 min readLW link

Be­ing an in­di­vi­d­ual al­ign­ment grantmaker

A_donor28 Feb 2022 20:02 UTC
64 points
5 comments2 min readLW link

Ukraine Post #1: Pre­dic­tion Markets

Zvi28 Feb 2022 19:20 UTC
67 points
0 comments16 min readLW link
(thezvi.wordpress.com)

Shah and Yud­kowsky on al­ign­ment failures

28 Feb 2022 19:18 UTC
85 points
39 comments91 min readLW link1 review

ELK Thought Dump

abramdemski28 Feb 2022 18:46 UTC
58 points
18 comments17 min readLW link

Con­spir­acy-proof archeology

Malmesbury27 Feb 2022 22:59 UTC
65 points
10 comments6 min readLW link

[David Chap­man] Re­sist­ing or em­brac­ing meta-rationality

Gordon Seidoh Worley27 Feb 2022 21:46 UTC
25 points
38 comments1 min readLW link
(metarationality.com)

[Question] Graphol­ogy posts.

Nocturnal Atavistic27 Feb 2022 20:50 UTC
0 points
0 comments1 min readLW link

How I Formed My Own Views About AI Safety

Neel Nanda27 Feb 2022 18:50 UTC
64 points
6 comments13 min readLW link
(www.neelnanda.io)

Brian Chris­tian AI Align­ment Lecture

Raj Thimmiah27 Feb 2022 18:13 UTC
3 points
0 comments1 min readLW link

South Bay ACX/​LW Meetup

IS27 Feb 2022 17:34 UTC
2 points
0 comments1 min readLW link

Defen­sive­ness as hys­ter­i­cal invisibility

TekhneMakre27 Feb 2022 15:28 UTC
6 points
5 comments2 min readLW link

Prepar­ing for Pos­si­ble Rus­sian Coun­ter­sanc­tions in Europe

arunto27 Feb 2022 12:01 UTC
25 points
9 comments1 min readLW link