Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
Archive
Sequences
About
Search
Log In
All
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
All
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
Dec
Page
2
ARC’s first technical report: Eliciting Latent Knowledge
paulfchristiano
,
Mark Xu
and
Ajeya Cotra
Dec 14, 2021, 8:09 PM
228
points
90
comments
1
min read
LW
link
3
reviews
(docs.google.com)
Morality is Scary
Wei Dai
Dec 2, 2021, 6:35 AM
228
points
116
comments
4
min read
LW
link
1
review
Whole Brain Emulation: No Progress on C. elegans After 10 Years
niconiconi
Oct 1, 2021, 9:44 PM
224
points
87
comments
5
min read
LW
link
2
reviews
What Do GDP Growth Curves Really Mean?
johnswentworth
Oct 7, 2021, 9:58 PM
222
points
64
comments
8
min read
LW
link
2
reviews
Gravity Turn
alkjash
Aug 16, 2021, 7:20 PM
220
points
21
comments
5
min read
LW
link
1
review
(radimentary.wordpress.com)
Utility Maximization = Description Length Minimization
johnswentworth
Feb 18, 2021, 6:04 PM
216
points
50
comments
6
min read
LW
link
Common knowledge about Leverage Research 1.0
BayAreaHuman
Sep 24, 2021, 6:56 AM
213
points
212
comments
5
min read
LW
link
Yudkowsky and Christiano discuss “Takeoff Speeds”
Eliezer Yudkowsky
Nov 22, 2021, 7:35 PM
210
points
176
comments
60
min read
LW
link
1
review
What’s So Bad About Ad-Hoc Mathematical Definitions?
johnswentworth
Mar 15, 2021, 9:51 PM
205
points
58
comments
7
min read
LW
link
Long Covid Is Not Necessarily Your Biggest Problem
Elizabeth
Sep 1, 2021, 7:20 AM
201
points
40
comments
10
min read
LW
link
(acesounderglass.com)
Almost everyone should be less afraid of lawsuits
alyssavance
Nov 27, 2021, 2:06 AM
198
points
18
comments
5
min read
LW
link
2
reviews
Shoulder Advisors 101
Duncan Sabien (Deactivated)
Oct 9, 2021, 5:30 AM
198
points
124
comments
14
min read
LW
link
2
reviews
Attempted Gears Analysis of AGI Intervention Discussion With Eliezer
Zvi
Nov 15, 2021, 3:50 AM
197
points
49
comments
16
min read
LW
link
(thezvi.wordpress.com)
Two non-obvious lessons from microcovid.org
catherio
Jun 24, 2021, 2:35 AM
196
points
4
comments
1
min read
LW
link
Birds, Brains, Planes, and AI: Against Appeals to the Complexity/Mysteriousness/Efficiency of the Brain
Daniel Kokotajlo
Jan 18, 2021, 12:08 PM
196
points
86
comments
13
min read
LW
link
1
review
Going Out With Dignity
Tomás B.
Jul 9, 2021, 10:07 PM
195
points
25
comments
6
min read
LW
link
1
review
Technological stagnation: Why I came around
jasoncrawford
Jan 23, 2021, 10:05 PM
193
points
79
comments
8
min read
LW
link
1
review
(rootsofprogress.org)
Takeaways from one year of lockdown
mingyuan
Mar 1, 2021, 3:53 AM
193
points
87
comments
6
min read
LW
link
Ruling Out Everything Else
Duncan Sabien (Deactivated)
Oct 27, 2021, 9:50 PM
193
points
51
comments
21
min read
LW
link
2
reviews
Zvi’s Thoughts on the Survival and Flourishing Fund (SFF)
Zvi
Dec 14, 2021, 2:30 PM
193
points
65
comments
64
min read
LW
link
1
review
(thezvi.wordpress.com)
Speaking of Stag Hunts
Duncan Sabien (Deactivated)
Nov 6, 2021, 8:20 AM
191
points
373
comments
18
min read
LW
link
Social behavior curves, equilibria, and radicalism
Eric Neyman
Jun 5, 2021, 1:39 AM
190
points
18
comments
20
min read
LW
link
1
review
(ericneyman.wordpress.com)
Power dynamics as a blind spot or blurry spot in our collective world-modeling, especially around AI
Andrew_Critch
Jun 1, 2021, 6:45 PM
189
points
26
comments
6
min read
LW
link
Split and Commit
Duncan Sabien (Deactivated)
Nov 21, 2021, 6:27 AM
188
points
34
comments
7
min read
LW
link
1
review
The case for aligning narrowly superhuman models
Ajeya Cotra
Mar 5, 2021, 10:29 PM
186
points
75
comments
38
min read
LW
link
1
review
The Rationalists of the 1950s (and before) also called themselves “Rationalists”
Owain_Evans
Nov 28, 2021, 8:17 PM
186
points
32
comments
3
min read
LW
link
1
review
How factories were made safe
jasoncrawford
Sep 12, 2021, 7:58 PM
185
points
46
comments
18
min read
LW
link
1
review
(rootsofprogress.org)
Simulacrum 3 As Stag-Hunt Strategy
johnswentworth
Jan 26, 2021, 7:40 PM
183
points
37
comments
4
min read
LW
link
3
reviews
The topic is not the content
Aaron Bergman
Jul 6, 2021, 12:14 AM
182
points
25
comments
5
min read
LW
link
(aaronbergman.substack.com)
The Point of Trade
Eliezer Yudkowsky
Jun 22, 2021, 5:56 PM
178
points
77
comments
4
min read
LW
link
1
review
The Best Software For Every Need
Tomás B.
Sep 10, 2021, 2:40 AM
178
points
225
comments
1
min read
LW
link
Announcing the Alignment Research Center
paulfchristiano
Apr 26, 2021, 11:30 PM
178
points
6
comments
1
min read
LW
link
(ai-alignment.com)
Jean Monnet: The Guerilla Bureaucrat
Martin Sustrik
Mar 20, 2021, 10:37 AM
177
points
25
comments
18
min read
LW
link
1
review
Predictive Coding has been Unified with Backpropagation
lsusr
Apr 2, 2021, 9:42 PM
176
points
51
comments
2
min read
LW
link
Specializing in Problems We Don’t Understand
johnswentworth
Apr 10, 2021, 10:40 PM
175
points
29
comments
8
min read
LW
link
1
review
Book Launch: The Engines of Cognition
Ben Pace
Dec 21, 2021, 7:24 AM
174
points
56
comments
5
min read
LW
link
Reneging Prosocially
Duncan Sabien (Deactivated)
Nov 30, 2021, 7:01 PM
174
points
15
comments
17
min read
LW
link
1
review
I’m from a parallel Earth with much higher coordination: AMA
Ben Pace
and
Eliezer Yudkowsky
Apr 5, 2021, 10:09 PM
173
points
35
comments
61
min read
LW
link
1
review
Preprint is out! 100,000 lumens to treat seasonal affective disorder
Fabienne
Nov 12, 2021, 5:59 PM
170
points
10
comments
1
min read
LW
link
Can you control the past?
Joe Carlsmith
Aug 27, 2021, 7:39 PM
170
points
94
comments
47
min read
LW
link
1
review
[Link] Still Alive—Astral Codex Ten
jimrandomh
Jan 21, 2021, 11:20 PM
169
points
10
comments
1
min read
LW
link
(astralcodexten.substack.com)
2021 AI Alignment Literature Review and Charity Comparison
Larks
Dec 23, 2021, 2:06 PM
168
points
28
comments
73
min read
LW
link
Testing The Natural Abstraction Hypothesis: Project Intro
johnswentworth
Apr 6, 2021, 9:24 PM
168
points
41
comments
6
min read
LW
link
1
review
You are probably underestimating how good self-love can be
Charlie Rogers-Smith
Nov 14, 2021, 12:41 AM
168
points
19
comments
12
min read
LW
link
1
review
Worst-case thinking in AI alignment
Buck
Dec 23, 2021, 1:29 AM
167
points
18
comments
6
min read
LW
link
2
reviews
Pseudorandomness contest: prizes, results, and analysis
Eric Neyman
Jan 15, 2021, 6:24 AM
164
points
22
comments
20
min read
LW
link
(ericneyman.wordpress.com)
Outline of Galef’s “Scout Mindset”
Rob Bensinger
Aug 10, 2021, 12:16 AM
163
points
17
comments
14
min read
LW
link
The Coordination Frontier: Sequence Intro
Raemon
Sep 4, 2021, 10:11 PM
163
points
22
comments
6
min read
LW
link
1
review
The 2021 Less Wrong Darwin Game
lsusr
Sep 24, 2021, 9:16 PM
162
points
102
comments
9
min read
LW
link
Small and Vulnerable
sapphire
May 3, 2021, 4:55 AM
162
points
17
comments
4
min read
LW
link
Previous
Back to top
Next
N
W
F
A
C
D
E
F
G
H
I
Customize appearance
Current theme:
default
A
C
D
E
F
G
H
I
Less Wrong (text)
Less Wrong (link)
Invert colors
Reset to defaults
OK
Cancel
Hi, I’m Bobby the Basilisk! Click on the minimize button (
) to minimize the theme tweaker window, so that you can see what the page looks like with the current tweaked values. (But remember,
the changes won’t be saved until you click “OK”!
)
Theme tweaker help
Show Bobby the Basilisk
OK
Cancel