Archive
Sequences
About
Search
Log In
Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
RSS
oskarkraak
Karma:
3
All
Posts
Comments
New
Top
Old
When the Smarter AI Lies Better: Can Debate-Based Oversight Catch Deceptive Code
oskarkraak
6 Jul 2025 1:21 UTC
4
points
0
comments
5
min read
LW
link
(oskarkraak.com)
Back to top