Archive
Sequences
About
Search
Log In
Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
RSS
jwfiredragon
Karma:
63
All
Posts
Comments
New
Top
Old
Untrusted monitoring insights from watching ChatGPT play coordination games
jwfiredragon
29 Jan 2025 4:53 UTC
14
points
8
comments
9
min read
LW
link
″… than average” is (almost) meaningless
jwfiredragon
21 Jun 2024 4:42 UTC
16
points
6
comments
3
min read
LW
link
An AI, a box, and a threat
jwfiredragon
7 Mar 2024 6:15 UTC
10
points
0
comments
6
min read
LW
link
Beware the suboptimal routine
jwfiredragon
10 Jan 2024 19:02 UTC
13
points
3
comments
3
min read
LW
link
Back to top