Archive
Sequences
About
Search
Log In
Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
RSS
New
Hot
Active
Old
Page
1
[Question]
If only the most powerful AGI is misaligned, can it be used as a doomsday machine?
StanislavKrym
13 May 2025 18:12 UTC
−3
points
0
comments
1
min read
LW
link
Optimization & AI Risk
atharva
13 May 2025 15:15 UTC
16
points
0
comments
1
min read
LW
link
How To Help Neglected Animals
omnizoid
13 May 2025 15:07 UTC
−4
points
1
comment
8
min read
LW
link
Too Soon
Gordon Seidoh Worley
13 May 2025 15:01 UTC
142
points
4
comments
4
min read
LW
link
Work as meditation
pchvykov
13 May 2025 12:02 UTC
20
points
3
comments
7
min read
LW
link
Levels of Republicanism
Benquo
13 May 2025 8:35 UTC
23
points
3
comments
6
min read
LW
link
(benjaminrosshoffman.com)
Caplan’s being melodramatic about circumcision
Yair Halberstadt
13 May 2025 5:27 UTC
−20
points
0
comments
2
min read
LW
link
AI Doomerism in 1879
David Gross
13 May 2025 2:48 UTC
84
points
3
comments
8
min read
LW
link
No-self as an alignment target
Milan W
13 May 2025 1:48 UTC
33
points
4
comments
1
min read
LW
link
Neo-solid Modernity—Crisis of Incoherence
Momcilo
12 May 2025 19:36 UTC
−1
points
1
comment
4
min read
LW
link
Measuring Schelling Coordination—Reflections on Subversion Strategy Eval
Graeme Ford
12 May 2025 19:06 UTC
3
points
0
comments
8
min read
LW
link
Procrastination is not real, it can’t hurt you
Mayank Goel
12 May 2025 19:00 UTC
1
point
16
comments
4
min read
LW
link
(mayankgoel28.substack.com)
How to title your blog post or whatever
dynomight
12 May 2025 18:12 UTC
24
points
6
comments
4
min read
LW
link
(dynomight.net)
Political sycophancy as a model organism of scheming
Alex Mallen
and
Vivek Hebbar
12 May 2025 17:49 UTC
39
points
0
comments
14
min read
LW
link
Things I Learned Making The SB-1047 Documentary
Michaël Trazzi
12 May 2025 17:41 UTC
60
points
2
comments
2
min read
LW
link
[Beneath Psychology] Introduction Part 1: The Challenge
jimmy
12 May 2025 17:01 UTC
5
points
2
comments
3
min read
LW
link
PSA: The LessWrong Feedback Service
JustisMills
12 May 2025 16:34 UTC
165
points
9
comments
2
min read
LW
link
Absolute Zero: Reinforced Self-play Reasoning with Zero Data
Matrice Jacobine
12 May 2025 15:20 UTC
5
points
4
comments
1
min read
LW
link
(www.arxiv.org)
AIs at the current capability level may be important for future safety work
ryan_greenblatt
12 May 2025 14:06 UTC
77
points
2
comments
4
min read
LW
link
[Question]
Game theory of “Nuclear Prisoner’s Dilemma”—on nuking rocks
CronoDAS
12 May 2025 11:07 UTC
11
points
6
comments
2
min read
LW
link
Back to top
Next