[Weekly Event] Align­ment Re­searcher Coffee Time (in Walled Gar­den)

adamShimi2 May 2021 12:59 UTC
37 points
0 comments1 min readLW link

[Linkpost] Teach­ing Para­dox, Europa Univer­alis IV, Part I: State of Play

adamShimi2 May 2021 9:02 UTC
17 points
5 comments1 min readLW link
(acoup.blog)

Car Seats Three Across

jefftk2 May 2021 2:00 UTC
16 points
0 comments1 min readLW link
(www.jefftk.com)

Ar­gu­ing from a Gap of Perspective

ideenrun1 May 2021 22:42 UTC
6 points
1 comment19 min readLW link

Fol­low-up to Ju­lia Wise on “Don’t Shoot The Dog”

Alex Flint1 May 2021 19:07 UTC
19 points
4 comments8 min readLW link

Death by Red Tape

abramdemski1 May 2021 18:03 UTC
38 points
15 comments3 min readLW link

Fore­cast­ing Newslet­ter: April 2021

NunoSempere1 May 2021 16:07 UTC
9 points
0 comments10 min readLW link

April 2021 Deep Dive: Trans­form­ers and GPT-3

adamShimi1 May 2021 11:18 UTC
31 points
6 comments7 min readLW link

Your Dog is Even Smarter Than You Think

StyleOfDog1 May 2021 5:16 UTC
254 points
108 comments9 min readLW link2 reviews

[ACX Linkpost] A Modest Pro­posal for Republicans

mike_hawke30 Apr 2021 18:43 UTC
9 points
3 comments1 min readLW link
(astralcodexten.substack.com)

Re­view of “Why AI is Harder Than We Think”

electroswing30 Apr 2021 18:14 UTC
40 points
10 comments8 min readLW link

Mind­ful­ness as debugging

pchvykov30 Apr 2021 16:59 UTC
21 points
4 comments2 min readLW link

Mo­ral Privilege

ACrackedPot30 Apr 2021 14:54 UTC
13 points
21 comments3 min readLW link

[Let­ter] Ad­vice for High School #2

lsusr30 Apr 2021 8:42 UTC
38 points
16 comments13 min readLW link

[Question] When’s the best time to get the 2nd dose of Pfizer Vac­cine?

David Scott Krueger (formerly: capybaralet)30 Apr 2021 5:11 UTC
5 points
3 comments1 min readLW link

On silence

Aaron Bergman30 Apr 2021 3:15 UTC
48 points
16 comments9 min readLW link
(aaronbergman.substack.com)

[Question] How do you so­licit feed­back effec­tively?

Raj Thimmiah30 Apr 2021 0:16 UTC
2 points
1 comment1 min readLW link

Low-stakes alignment

paulfchristiano30 Apr 2021 0:10 UTC
86 points
11 comments7 min readLW link1 review
(ai-alignment.com)

Why “is ev­i­dence for” is a sym­met­ric relation

alex_hhr29 Apr 2021 21:26 UTC
0 points
0 comments1 min readLW link
(raginrayguns.tumblr.com)

[Question] Where do LessWrong ra­tio­nal­ists de­bate?

Viliam29 Apr 2021 21:23 UTC
44 points
14 comments2 min readLW link

Scott Alexan­der 2021 pre­dic­tions: cal­ibra­tion and up­dat­ing exercise

Rob Bensinger29 Apr 2021 19:15 UTC
19 points
2 comments7 min readLW link

We need a ca­reer path for invention

jasoncrawford29 Apr 2021 18:11 UTC
51 points
18 comments4 min readLW link
(rootsofprogress.org)

25 Min Talk on Me­taEth­i­cal.AI with Ques­tions from Stu­art Armstrong

June Ku29 Apr 2021 15:38 UTC
21 points
7 comments1 min readLW link

On Ch­ester­ton’s Fence

Martin Sustrik29 Apr 2021 14:56 UTC
3 points
9 comments2 min readLW link

Covid 4/​29: Vac­ci­na­tion Slowdown

Zvi29 Apr 2021 13:50 UTC
55 points
19 comments15 min readLW link
(thezvi.wordpress.com)

Draft re­port on ex­is­ten­tial risk from power-seek­ing AI

Joe Carlsmith28 Apr 2021 21:41 UTC
85 points
23 comments1 min readLW link

Notes on Robert McIn­tyre’s Brain Preser­va­tion Talk at the Long Now Foundation

JohnGreer28 Apr 2021 20:47 UTC
14 points
2 comments13 min readLW link

AMA: Paul Chris­ti­ano, al­ign­ment researcher

paulfchristiano28 Apr 2021 18:55 UTC
117 points
197 comments1 min readLW link

[Question] Is sit­ting in the sun much bet­ter than sit­ting in the shade?

just_browsing28 Apr 2021 18:48 UTC
16 points
5 comments1 min readLW link

[AN #148]: An­a­lyz­ing gen­er­al­iza­tion across more axes than just ac­cu­racy or loss

Rohin Shah28 Apr 2021 18:30 UTC
24 points
5 comments11 min readLW link
(mailchi.mp)

Face­book is Si­mu­lacra Level 3, An­dreessen is Level 4

Ben Pace28 Apr 2021 17:38 UTC
52 points
12 comments2 min readLW link

When Should the Fire Alarm Go Off: A model for op­ti­mal thresholds

peterbarnett28 Apr 2021 12:27 UTC
40 points
4 comments5 min readLW link
(peterbarnett.org)

Bet­ter air is the eas­iest way not to die

digital_carver28 Apr 2021 10:24 UTC
23 points
9 comments1 min readLW link
(dynomight.net)

Nam­ing and poin­ter thickness

Adam Zerner28 Apr 2021 6:35 UTC
22 points
5 comments2 min readLW link

Talk­ers and doers

Amir Bolous28 Apr 2021 4:26 UTC
−1 points
3 comments1 min readLW link

A ca­sual in­tro to Geo­met­ric Algebra

Orfeas28 Apr 2021 0:00 UTC
24 points
2 comments6 min readLW link

Faerie Ring meet #2: At Gather.Town

hamnox27 Apr 2021 23:17 UTC
15 points
0 comments1 min readLW link

Ra­tion­al­ity Cardinality

jimrandomh27 Apr 2021 22:27 UTC
57 points
7 comments1 min readLW link

Pit­falls of the agent model

Alex Flint27 Apr 2021 22:19 UTC
25 points
5 comments20 min readLW link

[Question] Covid-19 in In­dia: Why didn’t it hap­pen ear­lier?

Sherrinford27 Apr 2021 19:13 UTC
14 points
5 comments1 min readLW link

Jaan Tal­linn’s 2020 Philan­thropy Overview

jaan27 Apr 2021 16:22 UTC
113 points
4 comments1 min readLW link
(jaan.online)

Scott Alexan­der 2021 Pre­dic­tions: Mar­ket Prices

SimonM27 Apr 2021 14:03 UTC
51 points
5 comments2 min readLW link

Modern Mone­tary The­ory for Dummies

theflowerpot27 Apr 2021 13:11 UTC
7 points
5 comments5 min readLW link

[Question] Can you im­prove IQ by prac­tic­ing IQ tests?

ForensicOceanography27 Apr 2021 11:28 UTC
8 points
43 comments1 min readLW link

Agents Over Carte­sian World Models

27 Apr 2021 2:06 UTC
66 points
4 comments27 min readLW link

[Question] What top­ics are on Dath Ilan’s civics exam?

jimrandomh27 Apr 2021 0:59 UTC
48 points
38 comments1 min readLW link

Scott Alexan­der 2021 Pre­dic­tions: Buy/​Sell/​Hold

Zvi27 Apr 2021 0:40 UTC
42 points
39 comments12 min readLW link
(thezvi.wordpress.com)

An­nounc­ing the Align­ment Re­search Center

paulfchristiano26 Apr 2021 23:30 UTC
178 points
6 comments1 min readLW link
(ai-alignment.com)

[Linkpost] Treach­er­ous turns in the wild

Mark Xu26 Apr 2021 22:51 UTC
31 points
6 comments1 min readLW link
(lukemuehlhauser.com)

FAQ: Ad­vice for AI Align­ment Researchers

Rohin Shah26 Apr 2021 18:59 UTC
67 points
2 comments1 min readLW link
(rohinshah.com)