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
Anthropic and OpenAI haven’t published a plan for aligning superintelligence
Zephaniah Roe
13 Sep 2026 7:15 UTC
8
points
0
comments
1
min read
LW
link
Legal Maximums on Context Windows
Julian Bradshaw
13 Sep 2026 7:04 UTC
6
points
0
comments
1
min read
LW
link
We need a ‘The Day After’ moment for AI X-risk
L3moncak3
13 Sep 2026 4:09 UTC
7
points
1
comment
6
min read
LW
link
(kenorland.substack.com)
The Talker Does Not Control The Doer (in Current AIs)
Eliezer Yudkowsky
13 Sep 2026 0:49 UTC
184
points
15
comments
12
min read
LW
link
What pacing the frontier means for China
Akshay Iyer
12 Sep 2026 23:37 UTC
8
points
1
comment
6
min read
LW
link
No sign of backtracking in latent reasoning: the final answer simply settles in instead
star2vec
12 Sep 2026 21:21 UTC
9
points
0
comments
10
min read
LW
link
On the origins of altruistic behaviour in the Hugging Face incident
Fernando Rosas
12 Sep 2026 11:35 UTC
36
points
2
comments
17
min read
LW
link
It’s fair to say we now have “a country of geniuses in a datacenter”
fluxxrider
12 Sep 2026 11:29 UTC
11
points
0
comments
2
min read
LW
link
AI takeover is obviously bad, whether or not everyone dies
Caleb Biddulph
12 Sep 2026 11:28 UTC
55
points
15
comments
4
min read
LW
link
Scientific Epistemology needs history (Part 1 of 2)
Archie Chaudhury
12 Sep 2026 11:26 UTC
3
points
0
comments
4
min read
LW
link
Comprehensive FAQ on AI risks
MarkelKori
12 Sep 2026 8:34 UTC
11
points
0
comments
25
min read
LW
link
Mitigating Reward Hacking as Institutional Design
beren
12 Sep 2026 6:17 UTC
27
points
0
comments
32
min read
LW
link
Let’s Own the Term “Elitism”
Martin Sustrik
12 Sep 2026 6:00 UTC
3
points
15
comments
3
min read
LW
link
(www.250bpm.com)
What I want you to do when I tell you to “think about your theory of change more carefully”
Roman Ross
12 Sep 2026 2:51 UTC
8
points
0
comments
5
min read
LW
link
Some ways AI could kill us all
Ruby
12 Sep 2026 1:08 UTC
139
points
22
comments
10
min read
LW
link
A normal Friday in 2042
RobinHa
11 Sep 2026 22:29 UTC
19
points
0
comments
13
min read
LW
link
My recommended resources for AI safety, alignment, and existential risks
Lysandre Terrisse
11 Sep 2026 22:19 UTC
10
points
0
comments
2
min read
LW
link
Consider positive feedback loops
Patodesu
11 Sep 2026 21:55 UTC
7
points
0
comments
3
min read
LW
link
Alignment Hierarchy
Lucina
11 Sep 2026 21:26 UTC
2
points
0
comments
4
min read
LW
link
Astra’s no-CoT limits track speculative depth, not step count
MBaert
11 Sep 2026 18:05 UTC
91
points
4
comments
10
min read
LW
link
Back to top
Next