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
All
Jan
Feb
Mar
Apr
May
Jun
Jul
Page
1
Where I agree and disagree with Eliezer
paulfchristiano
19 Jun 2022 19:15 UTC
684
points
191
comments
20
min read
LW
link
AGI Ruin: A List of Lethalities
Eliezer Yudkowsky
5 Jun 2022 22:05 UTC
666
points
629
comments
30
min read
LW
link
What an actually pessimistic containment strategy looks like
lc
5 Apr 2022 0:19 UTC
510
points
133
comments
6
min read
LW
link
Counter-theses on Sleep
Natália Coelho Mendonça
21 Mar 2022 23:21 UTC
401
points
131
comments
15
min read
LW
link
It Looks Like You’re Trying To Take Over The World
gwern
9 Mar 2022 16:35 UTC
376
points
124
comments
1
min read
LW
link
(www.gwern.net)
It’s Probably Not Lithium
Natália Coelho Mendonça
28 Jun 2022 21:24 UTC
347
points
112
comments
27
min read
LW
link
What DALL-E 2 can and cannot do
Swimmer963
1 May 2022 23:51 UTC
336
points
297
comments
9
min read
LW
link
MIRI announces new “Death With Dignity” strategy
Eliezer Yudkowsky
2 Apr 2022 0:43 UTC
324
points
518
comments
18
min read
LW
link
Reflections on six months of fatherhood
jasoncrawford
31 Jan 2022 5:28 UTC
321
points
21
comments
4
min read
LW
link
(jasoncrawford.org)
Accounting For College Costs
johnswentworth
1 Apr 2022 17:28 UTC
318
points
40
comments
7
min read
LW
link
Lies Told To Children
Eliezer Yudkowsky
14 Apr 2022 11:25 UTC
306
points
94
comments
7
min read
LW
link
Security Mindset: Lessons from 20+ years of Software Security Failures Relevant to AGI Alignment
elspood
21 Jun 2022 23:55 UTC
294
points
34
comments
7
min read
LW
link
Epistemic Legibility
Elizabeth
9 Feb 2022 18:10 UTC
280
points
28
comments
20
min read
LW
link
(acesounderglass.com)
Is AI Progress Impossible To Predict?
alyssavance
15 May 2022 18:30 UTC
263
points
38
comments
2
min read
LW
link
Six Dimensions of Operational Adequacy in AGI Projects
Eliezer Yudkowsky
30 May 2022 17:00 UTC
255
points
65
comments
13
min read
LW
link
We Choose To Align AI
johnswentworth
1 Jan 2022 20:06 UTC
247
points
15
comments
3
min read
LW
link
12 interesting things I learned studying the discovery of nature’s laws
Ben Pace
19 Feb 2022 23:39 UTC
245
points
40
comments
9
min read
LW
link
Beware boasting about non-existent forecasting track records
Jotto999
20 May 2022 19:20 UTC
241
points
109
comments
5
min read
LW
link
Don’t die with dignity; instead play to your outs
Jeffrey Ladish
6 Apr 2022 7:53 UTC
235
points
58
comments
5
min read
LW
link
Why Agent Foundations? An Overly Abstract Explanation
johnswentworth
25 Mar 2022 23:17 UTC
231
points
51
comments
8
min read
LW
link
(briefly) RaDVaC and SMTM, two things we should be doing
Eliezer Yudkowsky
12 Jan 2022 6:20 UTC
230
points
78
comments
3
min read
LW
link
A Quick Guide to Confronting Doom
Ruby
13 Apr 2022 19:30 UTC
222
points
36
comments
2
min read
LW
link
Contra Hofstadter on GPT-3 Nonsense
rictic
15 Jun 2022 21:53 UTC
222
points
18
comments
2
min read
LW
link
An Observation of Vavilov Day
Elizabeth
3 Jan 2022 21:10 UTC
219
points
42
comments
3
min read
LW
link
(acesounderglass.com)
Editing Advice for LessWrong Users
JustisMills
11 Apr 2022 16:32 UTC
215
points
13
comments
6
min read
LW
link
AGI Safety FAQ / all-dumb-questions-allowed thread
Aryeh Englander
7 Jun 2022 5:47 UTC
215
points
488
comments
4
min read
LW
link
Comment reply: my low-quality thoughts on why CFAR didn’t get farther with a “real/efficacious art of rationality”
AnnaSalamon
9 Jun 2022 2:12 UTC
215
points
59
comments
17
min read
LW
link
Replacing Karma with Good Heart Tokens (Worth $1!)
Ben Pace
and
habryka
1 Apr 2022 9:31 UTC
211
points
191
comments
4
min read
LW
link
Humans are very reliable agents
alyssavance
16 Jun 2022 22:02 UTC
206
points
27
comments
3
min read
LW
link
New Scaling Laws for Large Language Models
1a3orn
1 Apr 2022 20:41 UTC
205
points
20
comments
5
min read
LW
link
A central AI alignment problem: capabilities generalization, and the sharp left turn
So8res
15 Jun 2022 13:10 UTC
200
points
36
comments
10
min read
LW
link
Visible Homelessness in SF: A Quick Breakdown of Causes
alyssavance
25 May 2022 1:40 UTC
193
points
40
comments
2
min read
LW
link
Slow motion videos as AI risk intuition pumps
Andrew_Critch
14 Jun 2022 19:31 UTC
193
points
35
comments
2
min read
LW
link
On saving one’s world
Rob Bensinger
17 May 2022 19:53 UTC
189
points
5
comments
1
min read
LW
link
Moses and the Class Struggle
lsusr
1 Apr 2022 11:55 UTC
188
points
24
comments
5
min read
LW
link
Call For Distillers
johnswentworth
4 Apr 2022 18:25 UTC
186
points
36
comments
3
min read
LW
link
ProjectLawful.com: Eliezer’s latest story, past 1M words
Eliezer Yudkowsky
11 May 2022 6:18 UTC
185
points
93
comments
1
min read
LW
link
A concrete bet offer to those with short AI timelines
Matthew Barnett
and
Tamay
9 Apr 2022 21:41 UTC
184
points
93
comments
4
min read
LW
link
Benign Boundary Violations
Duncan_Sabien
26 May 2022 6:48 UTC
184
points
83
comments
18
min read
LW
link
dalle2 comments
nostalgebraist
26 Apr 2022 5:30 UTC
183
points
13
comments
13
min read
LW
link
(nostalgebraist.tumblr.com)
Postmortem on DIY Recombinant Covid Vaccine
caffemacchiavelli
22 Jan 2022 14:12 UTC
177
points
27
comments
5
min read
LW
link
Do a cost-benefit analysis of your technology usage
TurnTrout
27 Mar 2022 23:09 UTC
173
points
53
comments
13
min read
LW
link
Optimality is the tiger, and agents are its teeth
Veedrac
2 Apr 2022 0:46 UTC
172
points
28
comments
16
min read
LW
link
Have You Tried Hiring People?
rank-biserial
2 Mar 2022 2:06 UTC
172
points
120
comments
8
min read
LW
link
We Are Conjecture, A New Alignment Research Startup
Connor Leahy
8 Apr 2022 11:40 UTC
171
points
24
comments
4
min read
LW
link
Looking back on my alignment PhD
TurnTrout
1 Jul 2022 3:19 UTC
171
points
8
comments
11
min read
LW
link
Russia has Invaded Ukraine
lsusr
24 Feb 2022 7:52 UTC
165
points
270
comments
3
min read
LW
link
What’s Up With Confusingly Pervasive Consequentialism?
Raemon
20 Jan 2022 19:22 UTC
164
points
88
comments
4
min read
LW
link
Playing with DALL·E 2
Dave Orr
7 Apr 2022 18:49 UTC
164
points
116
comments
6
min read
LW
link
AI Could Defeat All Of Us Combined
HoldenKarnofsky
9 Jun 2022 15:50 UTC
163
points
28
comments
17
min read
LW
link
(www.cold-takes.com)
Back to top
Next