Utility functions are a good model to use if we’re talking about designing an AI. We want an AI to be predictable, to have stable preferences, and do what we want.
Why would these desirable features be the result? It reads to me as if you’re saying that this is a solution to the Friendly AI problem. Surely not?
Why would these desirable features be the result? It reads to me as if you’re saying that this is a solution to the Friendly AI problem. Surely not?
I am afraid he probably does. That’s the Yudkowskian notion of “friendly”. Not a very good word to describe it, IMHO.