Guild of Ser­vants Bac­cha­na­lia (March 27, 2021)

moridinamael26 Mar 2021 16:35 UTC
12 points
1 comment1 min readLW link

Co­her­ence ar­gu­ments im­ply a force for goal-di­rected behavior

KatjaGrace26 Mar 2021 16:10 UTC
91 points
24 comments11 min readLW link1 review
(aiimpacts.org)

Where did the idea of x-risk come from?

fowlertm26 Mar 2021 15:39 UTC
−8 points
2 comments1 min readLW link

Learn and prac­tice us­ing Han­lon’s Ra­zor with ex­er­cises.

icompetetowin26 Mar 2021 14:20 UTC
−7 points
2 comments1 min readLW link
(newsletter.decisionschool.org)

CFAR rEUnion (Septem­ber 24-27, 2021)

Jiří Nádvorník26 Mar 2021 10:51 UTC
33 points
0 comments1 min readLW link

Com­mu­ni­ca­tion Re­quires Com­mon In­ter­ests or Differ­en­tial Sig­nal Costs

Zack_M_Davis26 Mar 2021 6:41 UTC
40 points
13 comments3 min readLW link1 review

Toward A Bayesian The­ory Of Willpower

Scott Alexander26 Mar 2021 2:33 UTC
102 points
28 comments6 min readLW link

Some things I’ve learned in college

Aaron Bergman25 Mar 2021 21:30 UTC
22 points
1 comment7 min readLW link
(aaronbergman.substack.com)

Use your ra­tio­nal­ity or it’s useless

XxX25 Mar 2021 21:23 UTC
4 points
1 comment1 min readLW link

Money Buys Happiness

XxX25 Mar 2021 21:02 UTC
0 points
2 comments1 min readLW link

Call to the tech­ni­cal sup­port of reality

bayesyatina25 Mar 2021 20:05 UTC
8 points
2 comments1 min readLW link

The dan­ger of er­ror descriptions

gistya25 Mar 2021 20:05 UTC
−1 points
2 comments3 min readLW link

Austin Vir­tual Meetup 3/​27: Cal­ibra­tion prac­tice with Wits and Wagers

SilasBarta25 Mar 2021 17:53 UTC
9 points
0 comments1 min readLW link

On lan­guage mod­el­ing and fu­ture ab­stract rea­son­ing research

alexlyzhov25 Mar 2021 17:43 UTC
3 points
1 comment1 min readLW link
(docs.google.com)

[Question] Is a Self-Iter­at­ing AGI Vuln­er­a­ble to Thomp­son-style Tro­jans?

sxae25 Mar 2021 14:46 UTC
15 points
6 comments3 min readLW link

Covid 3/​25: Own Goals

Zvi25 Mar 2021 13:50 UTC
80 points
17 comments19 min readLW link
(thezvi.wordpress.com)

My AGI Threat Model: Misal­igned Model-Based RL Agent

Steven Byrnes25 Mar 2021 13:45 UTC
68 points
40 comments16 min readLW link

The Strange Case of the Amar­illo Option

adaminoue25 Mar 2021 6:16 UTC
5 points
0 comments1 min readLW link
(inoue.substack.com)

The best fre­quently don’t rise to the top

Adam Zerner25 Mar 2021 6:10 UTC
34 points
37 comments4 min readLW link

Cu­ri­os­ity needs courage

Amir Bolous25 Mar 2021 3:38 UTC
24 points
1 comment3 min readLW link

Why 1-box­ing doesn’t im­ply back­wards causation

Chris_Leong25 Mar 2021 2:32 UTC
7 points
14 comments4 min readLW link

Write a busi­ness plan already

bfinn25 Mar 2021 0:13 UTC
17 points
14 comments7 min readLW link

How You Can Gain Self Con­trol Without “Self-Con­trol”

spencerg24 Mar 2021 23:38 UTC
109 points
41 comments23 min readLW link

Magic Shoes

onur24 Mar 2021 21:14 UTC
11 points
0 comments3 min readLW link

[Question] Why is COVID re­in­fec­tion rate still so un­cer­tain.

gleb24 Mar 2021 21:12 UTC
1 point
4 comments1 min readLW link

[AN #143]: How to make em­bed­ded agents that rea­son prob­a­bil­is­ti­cally about their environments

Rohin Shah24 Mar 2021 17:20 UTC
13 points
3 comments8 min readLW link
(mailchi.mp)

[Question] What does the re­ac­tion to NFTs tell us about how peo­ple eval­u­ate ecolog­i­cal dam­age?

sxae24 Mar 2021 16:01 UTC
1 point
5 comments2 min readLW link

The Price Of Space Is Friendship

sxae24 Mar 2021 11:27 UTC
13 points
19 comments3 min readLW link

Toy model of prefer­ence, bias, and ex­tra information

Stuart_Armstrong24 Mar 2021 10:14 UTC
9 points
0 comments4 min readLW link

Sel­ling At­ten­tion for Money

MikkW24 Mar 2021 6:24 UTC
24 points
2 comments4 min readLW link

Another RadVac Test­ing Update

johnswentworth23 Mar 2021 17:29 UTC
138 points
19 comments5 min readLW link

Mary and the Black And White Me­mory Implant

sxae23 Mar 2021 16:48 UTC
−2 points
24 comments2 min readLW link

Prefer­ences and bi­ases, the in­for­ma­tion argument

Stuart_Armstrong23 Mar 2021 12:44 UTC
14 points
5 comments1 min readLW link

Against evolu­tion as an anal­ogy for how hu­mans will cre­ate AGI

Steven Byrnes23 Mar 2021 12:29 UTC
65 points
25 comments25 min readLW link

“In­fra-Bayesi­anism with Vanessa Kosoy” – Watch/​Dis­cuss Party

Ben Pace22 Mar 2021 23:44 UTC
27 points
45 comments1 min readLW link

Canada Covid Up­date: think­ing out loud

MalcolmOcean22 Mar 2021 21:39 UTC
35 points
6 comments3 min readLW link

Thirty-three ran­domly se­lected bioethics papers

Rob Bensinger22 Mar 2021 21:38 UTC
112 points
46 comments50 min readLW link

My re­search methodology

paulfchristiano22 Mar 2021 21:20 UTC
159 points
38 comments16 min readLW link1 review
(ai-alignment.com)

A Ret­ro­spec­tive Look at the Guild of Ser­vants: Alpha Phase

moridinamael22 Mar 2021 20:34 UTC
76 points
8 comments11 min readLW link

On fu­ture peo­ple, look­ing back at 21st cen­tury longtermism

Joe Carlsmith22 Mar 2021 8:23 UTC
39 points
3 comments12 min readLW link

Gen­er­al­iz­ing POWER to multi-agent games

22 Mar 2021 2:41 UTC
52 points
16 comments7 min readLW link

Mov­ing Data Around is Slow

SatvikBeri22 Mar 2021 2:36 UTC
35 points
10 comments2 min readLW link

Burmese Days, Mar 22; Rules of the Game and Prefer­ence Falsifi­ca­tion in the Army

Tim Liptrot22 Mar 2021 0:12 UTC
17 points
2 comments3 min readLW link

Six-Door Cars

jefftk21 Mar 2021 19:30 UTC
20 points
8 comments1 min readLW link
(www.jefftk.com)

De­mand offsetting

paulfchristiano21 Mar 2021 18:20 UTC
131 points
41 comments5 min readLW link
(sideways-view.com)

A parable of brightspots and blindspots

Remmelt21 Mar 2021 18:18 UTC
4 points
0 comments3 min readLW link

[event] Cry­on­ics icebreaker

Mati_Roy21 Mar 2021 17:44 UTC
16 points
2 comments1 min readLW link

Pro­cess Orientation

lincolnquirk21 Mar 2021 15:21 UTC
31 points
4 comments5 min readLW link

Gossip

Yoav Ravid21 Mar 2021 13:36 UTC
12 points
7 comments11 min readLW link

[Book Re­view] Destiny Disrupted

lsusr21 Mar 2021 7:09 UTC
58 points
4 comments9 min readLW link