We Will Likely Be Deceived by AIs, but This is Not Necessarily a Tragedy
I am wary of thinking about engineered AI systems in terms of revealed preferences. In this instance, I’m inclined to adopt Ken Binmore’s suggestion to speak of attributed, rather than revealed, preferences.
I am wary of thinking about engineered AI systems in terms of revealed preferences. In this instance, I’m inclined to adopt Ken Binmore’s suggestion to speak of attributed, rather than revealed, preferences.