Archive
Sequences
About
Search
Log In
Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
RSS
Misha Wagner
Karma:
42
All
Posts
Comments
New
Top
Old
Sabotage Evaluations for Frontier Models
David Duvenaud
,
evhub
,
Joe Benton
,
Misha Wagner
,
Eric Christiansen
,
Ethan Perez
,
Buck
,
HoldenKarnofsky
and
Sam Bowman
18 Oct 2024 22:33 UTC
65
points
0
comments
6
min read
LW
link
(assets.anthropic.com)
Back to top