This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
Tags
LW
Login
Auditing Games
•
Applied to
Hidden Cognition Detection Methods and Benchmarks
by
Paul Colognese
2mo
ago
•
Applied to
Automating Auditing: An ambitious concrete technical research proposal
by
Raemon
2y
ago
•
Applied to
A transparency and interpretability tech tree
by
Raemon
2y
ago
•
Applied to
Auditing games for high-level interpretability
by
Ruby
2y
ago
•
Created by
Ruby
at
2y