Yes, I kind of over-answered the question: I’m saying even if you have some optimization process that is not even an agent you can get instrumental “behaviors” that are not safe, let alone an agent that is not self-aware.
Yes, I kind of over-answered the question: I’m saying even if you have some optimization process that is not even an agent you can get instrumental “behaviors” that are not safe, let alone an agent that is not self-aware.