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]
Will we survive if AI solves engineering before deception?
Knight Lee
May 17, 2025, 7:22 PM
18
points
9
comments
1
min read
LW
link
Seven ways to Improve the Internal Model Principle
Alfred Harwood
May 17, 2025, 4:38 PM
7
points
0
comments
13
min read
LW
link
D&D.Sci: The Choosing Ones
abstractapplic
May 17, 2025, 3:26 PM
32
points
0
comments
1
min read
LW
link
The absent-minded variations
dr_s
May 17, 2025, 6:57 AM
17
points
2
comments
9
min read
LW
link
Book Review: The Art of Happiness
Screwtape
May 17, 2025, 4:56 AM
32
points
8
comments
11
min read
LW
link
Management is the Near Future
jefftk
May 17, 2025, 2:50 AM
44
points
5
comments
2
min read
LW
link
(www.jefftk.com)
Proof Section to an Introduction to Reinforcement Learning for Understanding Infra-Bayesianism
Brittany Gelb
May 17, 2025, 2:36 AM
3
points
0
comments
9
min read
LW
link
An Introduction to Reinforcement Learning for Understanding Infra-Bayesianism
Brittany Gelb
May 17, 2025, 2:34 AM
11
points
0
comments
20
min read
LW
link
Social Anxiety Isn’t About Being Liked
Chipmonk
May 16, 2025, 10:26 PM
68
points
17
comments
2
min read
LW
link
(chrislakin.blog)
How Fast Can Algorithms Advance Capabilities? | Epoch Gradient Update
henryj
May 16, 2025, 9:38 PM
28
points
5
comments
6
min read
LW
link
(epoch.ai)
P-Values Know When You’re Cheating
Eggs
May 16, 2025, 8:34 PM
20
points
1
comment
2
min read
LW
link
Minds are magic
k64
May 16, 2025, 7:10 PM
0
points
0
comments
2
min read
LW
link
Direct Realism is probably false
TerriLeaf
May 16, 2025, 4:36 PM
1
point
13
comments
3
min read
LW
link
Generating the Funniest Joke with RL (according to GPT-4.1)
agg
May 16, 2025, 5:09 AM
82
points
14
comments
4
min read
LW
link
Interpretable Fine Tuning Research Update and Working Prototype
Matthew Khoriaty
May 16, 2025, 3:44 AM
7
points
0
comments
4
min read
LW
link
It Is Untenable That Near-Future AI Scenario Models Like “AI 2027” Don’t Include Open Source AI
Andrew Dickson
May 16, 2025, 2:20 AM
29
points
17
comments
5
min read
LW
link
Starting Over: What to tell Sarah, at the edge of professional oblivion.
Brad Dunn
May 15, 2025, 9:34 PM
11
points
1
comment
20
min read
LW
link
Tax-Optimized Risk in Portfolio Allocation
Brendan Long
May 15, 2025, 6:53 PM
2
points
0
comments
1
min read
LW
link
(www.brendanlong.com)
Some skepticism about skepticism about efficacy of pausing AI
extinction-bounties
May 15, 2025, 6:15 PM
5
points
1
comment
2
min read
LW
link
Consider Others’ Cost Tolerances
nomagicpill
May 15, 2025, 5:43 PM
23
points
1
comment
4
min read
LW
link
(nomagicpill.github.io)
Back to top
Next