The speaker argues that distinguishing deceptive AI behavior from genuinely aligned behavior requires white-box understanding of AI internals.

“some sort of notion of like because you're going to fundamentally need to distinguish between the ais that's pretending to is you know is doing the nice thing because it's pretending and is waiting and biding time and the ai that fundamentally is doing the nice thing because it wants to do the nice thing and that i think will require sort of this white box like understanding of what's going on inside the ais whereas in the control thing you can just figure out via like empirical behavioral iteration um and so overall basically our story”