Ari Spiesberger

Model Organisms of Collusion: Corrective Transfer in Untrusted Monitors

AI control protocols aim to get useful work from models that may be misaligned by monitoring their behaviour. One approach uses a second copy of the same model as the monitor. This avoids relying on a weaker reviewer the model could outsmart, but risks collusion: the model, now monitoring itself, may cover up its own m...