AI: A Future for Humans
The Reith Lectures
Controlling the Machine's Preferences
Ai systems that know, they don't know the true objective, even though it's what they must pursue. I wrote these ideas down in the form of three principles. The first principle is that the machine's only objective is to maximize the realization of human preferences. We remove the false assumption that the machine is pursuing a fixed objective That is perfectly known. This principle is what gives us control, for reasons that will become clear soon. Third principle is that our ultimate source of information about an preferences is human behavior. Here, behavior means everything we do, which includes everything we say,. It also includes the entire written record, because most of what we write about is humans doing things and other
Remember Everything You Learn from Podcasts
