This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
AF
Login
Oliver Makins
I work on Control at UK AISI
Posts
Sorted by New
Wikitag Contributions
Comments
Sorted by
Newest
28
Misalignment classifiers: Why they’re hard to evaluate adversarially, and why we're studying them anyway
20d
0
Comments