Ryan Greenblatt says AI monitoring of other AIs can detect cheating, but is imperfect when the monitored activities are difficult to understand.

“And so even though we are still detecting all these incidents of AI's cheating,”

“and in fact, we can even get one AI to monitor another AI and be like, was it cheating?”

“That doesn't always perfectly work as we start moving into these domains where what the AIs are doing are really difficult to understand.”