Can AI Be Trusted? The Challenge of Alignment Faking

As so often. Where's the control? Why not have a models condition be to randomly respond to harmful prompts and have random observation of the reasoning?

I wonder how much of this is just our own way of anthropomorphizing something, just like we do when our car acts up and we swear at it. We look for human behavior in non human things.

Can Parrots Be Trusted? The Pitfalls of Personification

Rational Animations has an excellent video on trust here: https://www.youtube.com/watch?v=KUkHhVYv3jU