Covid 9/​30: Peo­ple Re­spond to Incentives

Zvi30 Sep 2021 18:40 UTC
49 points
14 comments17 min readLW link
(thezvi.wordpress.com)

Some Ex­ist­ing Selec­tion Theorems

johnswentworth30 Sep 2021 16:13 UTC
54 points
2 comments4 min readLW link

[Question] How can one train philo­soph­i­cal skill?

abramdemski30 Sep 2021 14:56 UTC
31 points
47 comments1 min readLW link

Take­off Speeds and Discontinuities

30 Sep 2021 13:50 UTC
63 points
1 comment15 min readLW link

Offer: free/​low-cost de­ci­sion sup­port ser­vices for world-im­prov­ing initiatives

Ian David Moss30 Sep 2021 13:21 UTC
5 points
0 comments4 min readLW link

My take on Vanessa Kosoy’s take on AGI safety

Steven Byrnes30 Sep 2021 12:23 UTC
97 points
10 comments31 min readLW link

AI learns be­trayal and how to avoid it

Stuart_Armstrong30 Sep 2021 9:39 UTC
30 points
4 comments2 min readLW link

Effec­tive Altru­ism Vir­tual Real­ity Meetup

Hamp30 Sep 2021 7:28 UTC
6 points
0 comments1 min readLW link

[Book re­view] Who we are and how we got here

mukashi30 Sep 2021 4:26 UTC
14 points
0 comments8 min readLW link

In­ter­view with Skynet

lsusr30 Sep 2021 2:20 UTC
49 points
1 comment2 min readLW link

[Pre­dic­tion] We are in an Al­gorith­mic Overhang

lsusr29 Sep 2021 23:40 UTC
31 points
14 comments1 min readLW link

Is­sues with Giv­ing Multiplier

jefftk29 Sep 2021 21:40 UTC
28 points
0 comments6 min readLW link
(www.jefftk.com)

The Mind Is A Shaky Con­trol System

DirectedEvolution29 Sep 2021 20:49 UTC
6 points
0 comments3 min readLW link

The role of tribes in achiev­ing last­ing im­pact and how to cre­ate them

29 Sep 2021 20:48 UTC
14 points
3 comments24 min readLW link

[Question] Wis­dom of the crowds?

amarai29 Sep 2021 19:14 UTC
2 points
2 comments1 min readLW link

[Book re­view] Gödel, Escher, Bach: an in-depth explainer

Sam Marks29 Sep 2021 19:03 UTC
98 points
23 comments23 min readLW link1 review

Easily Top 20%

Jacob Falkovich29 Sep 2021 18:24 UTC
37 points
0 comments10 min readLW link

Sex-Pos­i­tivity is Countercultural

Jacob Falkovich29 Sep 2021 18:22 UTC
39 points
2 comments3 min readLW link

A brief re­view of the rea­sons multi-ob­jec­tive RL could be im­por­tant in AI Safety Research

Ben Smith29 Sep 2021 17:09 UTC
31 points
7 comments10 min readLW link

Un­solved ML Safety Problems

jsteinhardt29 Sep 2021 16:00 UTC
59 points
2 comments3 min readLW link
(bounded-regret.ghost.io)

Brain-in­spired AGI and the “life­time an­chor”

Steven Byrnes29 Sep 2021 13:09 UTC
65 points
16 comments13 min readLW link

Bayeswatch 10: Spyware

lsusr29 Sep 2021 7:01 UTC
98 points
7 comments4 min readLW link

[Book Re­view] “Hou­dini on Magic” by Harry Houdini

lsusr29 Sep 2021 2:37 UTC
21 points
1 comment6 min readLW link

[Question] What Heuris­tics Do You Use to Think About Align­ment Topics?

Logan Riggs29 Sep 2021 2:31 UTC
5 points
3 comments1 min readLW link

A re­view of Steven Pinker’s new book on rationality

Matthew Barnett29 Sep 2021 1:29 UTC
140 points
43 comments6 min readLW link

D&D.Sci 4th Edi­tion: League of Defen­ders of the Storm

aphyer28 Sep 2021 23:19 UTC
42 points
31 comments3 min readLW link

Cryosleep

harsimony28 Sep 2021 22:33 UTC
9 points
3 comments5 min readLW link
(harsimony.wordpress.com)

You can talk to EA Funds be­fore applying

evhub28 Sep 2021 20:39 UTC
71 points
2 comments1 min readLW link

[Question] Col­lec­tion of ar­gu­ments to ex­pect (outer and in­ner) al­ign­ment failure?

Sam Clarke28 Sep 2021 16:55 UTC
21 points
10 comments1 min readLW link

[Question] Prob­lems with us­ing ap­proval vot­ing to elect to a multi-in­di­vi­d­ual body?

RyanCarey28 Sep 2021 11:03 UTC
8 points
13 comments1 min readLW link

Sun­screen: much more than you wanted to know

Pierre Vandenberghe28 Sep 2021 10:42 UTC
29 points
10 comments6 min readLW link
(pierreavdb.substack.com)

Selec­tion The­o­rems: A Pro­gram For Un­der­stand­ing Agents

johnswentworth28 Sep 2021 5:03 UTC
123 points
28 comments6 min readLW link2 reviews

Be­ware Su­perfi­cial Plausibility

Celer28 Sep 2021 3:58 UTC
32 points
13 comments4 min readLW link

In­ner Belt

jefftk28 Sep 2021 3:50 UTC
15 points
0 comments1 min readLW link
(www.jefftk.com)

Blood Is Thicker Than Water 🐬

Zack_M_Davis28 Sep 2021 3:21 UTC
37 points
26 comments13 min readLW link

Is progress in ML-as­sisted the­o­rem-prov­ing benefi­cial?

mako yass28 Sep 2021 1:54 UTC
11 points
3 comments1 min readLW link

EA Han­gout Pri­son­ers’ Dilemma

Jeffrey Ladish27 Sep 2021 23:15 UTC
55 points
18 comments3 min readLW link

[Book Re­view] “The Vi­tal Ques­tion” by Nick Lane

lsusr27 Sep 2021 22:50 UTC
70 points
26 comments7 min readLW link

Reach­a­bil­ity De­bates (Are Often In­visi­ble)

J Bostock27 Sep 2021 22:05 UTC
17 points
8 comments2 min readLW link

AISC5 Ret­ro­spec­tive: Mechanisms for Avoid­ing Tragedy of the Com­mons in Com­mon Pool Re­source Problems

27 Sep 2021 16:46 UTC
8 points
3 comments7 min readLW link

AI take­off story: a con­tinu­a­tion of progress by other means

Edouard Harris27 Sep 2021 15:55 UTC
76 points
13 comments10 min readLW link

The In­tense World The­ory of Autism

Steven Byrnes27 Sep 2021 13:23 UTC
100 points
29 comments14 min readLW link

A Con­fused Chemist’s Re­view of AlphaFold 2

J Bostock27 Sep 2021 11:10 UTC
23 points
4 comments5 min readLW link

The Trol­ley Problem

lsusr27 Sep 2021 8:26 UTC
31 points
25 comments2 min readLW link

Re­view: The End Is Always Near

Elizabeth27 Sep 2021 7:40 UTC
37 points
10 comments3 min readLW link
(acesounderglass.com)

Where’s my magic sword?

lsusr27 Sep 2021 7:26 UTC
44 points
12 comments2 min readLW link

Up­dates from Lev­er­age Re­search: His­tory and Re­cent Progress

LarissaRowe27 Sep 2021 5:23 UTC
37 points
4 comments9 min readLW link

[Question] How to mea­sure (hu­man) im­pact?

Fer32dwt34r3dfsz27 Sep 2021 2:32 UTC
7 points
2 comments1 min readLW link

100 Years Of Ex­is­ten­tial Risk

jdp27 Sep 2021 0:31 UTC
79 points
12 comments33 min readLW link
(www.wrestlinggnon.com)

[Question] Any write­ups on GPT agency?

Ozyrus26 Sep 2021 22:55 UTC
4 points
6 comments1 min readLW link