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
Some Meetups I Ran (2025 Q2)
jenn
1 Nov 2025 18:28 UTC
6
points
0
comments
6
min read
LW
link
[Question]
Shouldn’t taking over the world be easier than recursively self-improving, as an AI?
KvmanThinking
1 Nov 2025 17:26 UTC
7
points
0
comments
1
min read
LW
link
Fermi Paradox, Ethics and Astronomical waste
StanislavKrym
1 Nov 2025 15:24 UTC
3
points
0
comments
1
min read
LW
link
LLM-generated text is not testimony
TsviBT
1 Nov 2025 14:47 UTC
50
points
8
comments
11
min read
LW
link
Vaccination against ASI
dscft
1 Nov 2025 10:58 UTC
−1
points
3
comments
1
min read
LW
link
Strategy-Stealing Argument Against AI Dealmaking
Cleo Nardo
1 Nov 2025 4:39 UTC
10
points
1
comment
2
min read
LW
link
Evidence on language model consciousness
dsj
1 Nov 2025 4:01 UTC
16
points
0
comments
2
min read
LW
link
(thedavidsj.substack.com)
Asking Paul Fussell for Writing Advice
Taylor G. Lunt
1 Nov 2025 3:37 UTC
7
points
0
comments
8
min read
LW
link
Freewriting in my head, and overcoming the “twinge of starting”
ParrotRobot
1 Nov 2025 1:12 UTC
23
points
1
comment
6
min read
LW
link
Supervillain Monologues Are Unrealistic
Algon
31 Oct 2025 23:58 UTC
39
points
7
comments
2
min read
LW
link
Secretly Loyal AIs: Threat Vectors and Mitigation Strategies
Dave Banerjee
31 Oct 2025 23:31 UTC
5
points
0
comments
19
min read
LW
link
(substack.com)
FAQ: Expert Survey on Progress in AI methodology
KatjaGrace
31 Oct 2025 16:51 UTC
12
points
0
comments
19
min read
LW
link
(blog.aiimpacts.org)
Social media feeds ‘misaligned’ when viewed through AI safety framework, show researchers
Mordechai Rorvig
31 Oct 2025 16:40 UTC
13
points
3
comments
1
min read
LW
link
(www.foommagazine.org)
Debugging Despair ~> A bet about Satisfaction and Values
P. João
31 Oct 2025 14:00 UTC
3
points
0
comments
2
min read
LW
link
A (bad) Definition of AGI
spookyuser
31 Oct 2025 7:55 UTC
4
points
0
comments
5
min read
LW
link
Introducing Project Telos: Modeling, Measuring, and Intervening on Goal-directed Behaviour in AI Systems
Mario Giulianelli
31 Oct 2025 1:28 UTC
3
points
0
comments
8
min read
LW
link
Resampling Conserves Redundancy & Mediation (Approximately) Under the Jensen-Shannon Divergence
David Lorell
31 Oct 2025 1:07 UTC
37
points
6
comments
4
min read
LW
link
Centralization begets stagnation
Algon
30 Oct 2025 23:49 UTC
6
points
0
comments
2
min read
LW
link
Summary and Comments on Anthropic’s Pilot Sabotage Risk Report
GradientDissenter
30 Oct 2025 20:19 UTC
28
points
0
comments
5
min read
LW
link
Critical Fallibilism and Theory of Constraints in One Analyzed Paragraph
Elliot Temple
30 Oct 2025 20:06 UTC
1
point
0
comments
28
min read
LW
link
Back to top
Next