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
Sandy Blvd as an example of complexity
Adam Zerner
13 Jun 2026 0:28 UTC
7
points
0
comments
2
min read
LW
link
What’s Continual Learning, and Why Might We Expect To See It In Advanced LLM Agents?
RohanS
,
Rauno Arike
,
Owen Terry
,
Achu Menon
,
Zhijing Jin
,
Francis Rhys Ward
and
Seth Herd
12 Jun 2026 18:43 UTC
23
points
2
comments
17
min read
LW
link
Implications of Continual Learning for LLM Agents: Introduction
RohanS
,
Rauno Arike
,
Owen Terry
,
Achu Menon
,
Zhijing Jin
,
Francis Rhys Ward
and
Seth Herd
12 Jun 2026 18:36 UTC
39
points
0
comments
6
min read
LW
link
Reward Hacking at the 1937 World’s Fair
frmsaul
12 Jun 2026 17:47 UTC
41
points
3
comments
3
min read
LW
link
Bunk in AF
Fernand0
12 Jun 2026 17:41 UTC
6
points
0
comments
1
min read
LW
link
Building and evaluating model diffing agents
bilalchughtai
,
Josh Engels
and
Neel Nanda
12 Jun 2026 17:14 UTC
48
points
2
comments
12
min read
LW
link
“AF needs empirical grounding” is a meaningless valley of compromise
Fernand0
12 Jun 2026 16:37 UTC
8
points
0
comments
1
min read
LW
link
How bad would it be if GPS satellites were shot down?
Jackson Wagner
12 Jun 2026 16:34 UTC
16
points
0
comments
21
min read
LW
link
Sympathy for both sides of the egregious misalignment debate
Steven Byrnes
12 Jun 2026 16:26 UTC
120
points
9
comments
4
min read
LW
link
The Uncertainty That Matters Isn’t Fundamental
jimmy
12 Jun 2026 16:23 UTC
24
points
1
comment
13
min read
LW
link
Citations Needed: Magic Encyclopedias to Save the World
Oliver Sourbut
12 Jun 2026 15:35 UTC
35
points
1
comment
5
min read
LW
link
(www.oliversourbut.net)
If you, a human, can imagine red and green being swapped, you are probably conscious
vals tutor
12 Jun 2026 13:28 UTC
3
points
17
comments
7
min read
LW
link
Simulating Simulators
kromem
12 Jun 2026 12:56 UTC
34
points
2
comments
15
min read
LW
link
Parkinson’s Heuristic: The Only Time To Do Anything
Ben Pace
12 Jun 2026 6:55 UTC
79
points
5
comments
5
min read
LW
link
PSA: Almost nobody is directly working on superintelligent alignment
Chi Nguyen
and
peterbarnett
12 Jun 2026 5:17 UTC
189
points
26
comments
1
min read
LW
link
Honey is Good
G Wood
12 Jun 2026 4:07 UTC
9
points
2
comments
3
min read
LW
link
The Aestheticising Vice by Paul Seabright
Linch
12 Jun 2026 2:20 UTC
21
points
2
comments
2
min read
LW
link
Celene’s thoughts on consciousness
ToasterLightning
12 Jun 2026 0:55 UTC
46
points
32
comments
18
min read
LW
link
(terminuspoint.substack.com)
Construct validity of Claude Opus 4.8′s System Card – A commentary
Maria Federica Martino Lena
11 Jun 2026 23:33 UTC
7
points
0
comments
16
min read
LW
link
you won’t one-shot a perfect system, but try anyway
PossiblyElaine
11 Jun 2026 22:43 UTC
7
points
1
comment
4
min read
LW
link
(possiblyelaine.substack.com)
Back to top
Next