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
Satisfying Curiosity Isn’t the Same as Understanding
CstineSublime
3 Sep 2026 1:04 UTC
12
points
0
comments
1
min read
LW
link
Resolution has a new Agent Foundations team
Jeremy Gillen
3 Sep 2026 0:53 UTC
133
points
1
comment
2
min read
LW
link
(resolution.org)
What is neuralese and why is it bad?
Linch
2 Sep 2026 23:37 UTC
26
points
1
comment
3
min read
LW
link
(linch.substack.com)
Notes on “A global workspace in language models”
Shunk
2 Sep 2026 23:12 UTC
7
points
0
comments
5
min read
LW
link
The Return of Aspect Oriented Programming
thomascolthurst
2 Sep 2026 22:22 UTC
4
points
0
comments
4
min read
LW
link
The Three P’s Theory of Research Organizations
thomascolthurst
2 Sep 2026 22:19 UTC
5
points
0
comments
2
min read
LW
link
Talking to journalists
KatjaGrace
2 Sep 2026 21:52 UTC
29
points
0
comments
3
min read
LW
link
(worldspiritsockpuppet.substack.com)
A proposal for a highly effective AI safety org
ceselder
2 Sep 2026 21:34 UTC
33
points
4
comments
2
min read
LW
link
How concerned should we be about Astra’s recurrent architecture?
Rauno Arike
2 Sep 2026 18:28 UTC
78
points
8
comments
10
min read
LW
link
Two Paths from Logical Induction: Part 0
Ashe Vazquez Nuñez
2 Sep 2026 17:53 UTC
23
points
0
comments
12
min read
LW
link
Why OpenAI’s Astra Could Make AI Doom Harder to Prevent
Goutham Nalagatla
2 Sep 2026 16:35 UTC
12
points
3
comments
7
min read
LW
link
Life is not a social deduction game
Fernand0
2 Sep 2026 16:23 UTC
7
points
0
comments
1
min read
LW
link
The opposite of culty isn’t bland
Fernand0
2 Sep 2026 15:28 UTC
2
points
0
comments
3
min read
LW
link
Autonomy, Freedom and Control
Samuel Ratnam
2 Sep 2026 13:35 UTC
5
points
0
comments
4
min read
LW
link
(samuelratnam.substack.com)
If you’re interpreting <1B parameter models, you should use a tensor transformer
Logan Riggs
2 Sep 2026 13:20 UTC
37
points
0
comments
2
min read
LW
link
[Diagram] Early handoff? Improve conceptual reasoning?
Cleo Nardo
2 Sep 2026 12:35 UTC
26
points
2
comments
10
min read
LW
link
(clattubato.substack.com)
AI Co-operation and AI Alignment
drnickbone
2 Sep 2026 11:19 UTC
15
points
1
comment
2
min read
LW
link
Core Assumptions of ELK
Q Home
2 Sep 2026 10:04 UTC
12
points
0
comments
5
min read
LW
link
Incoherent AI Identities can also be Stable
Ashe Vazquez Nuñez
2 Sep 2026 2:21 UTC
32
points
0
comments
13
min read
LW
link
Don’t be the vitamin B guy
HedonicEscalator
2 Sep 2026 2:02 UTC
53
points
3
comments
6
min read
LW
link
(hedonicescalator.substack.com)
Back to top
Next