This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
LW
Login
oliverfm
I work on Control at UK AISI
Posts
Sorted by New
Wikitag Contributions
Comments
Sorted by
Newest
58
Misalignment classifiers: Why they’re hard to evaluate adversarially, and why we're studying them anyway
Ω
18d
Ω
3
Comments