Toggle navigation
OpenReview
.net
Login
×
Go to
DBLP
homepage
AI Control: Improving Safety Despite Intentional Subversion
Ryan Greenblatt
,
Buck Shlegeris
,
Kshitij Sachan
,
Fabien Roger
Published: 01 Jan 2024, Last Modified: 13 May 2025
ICML 2024
Everyone
Revisions
BibTeX
CC BY-SA 4.0
Loading