hal@finney.org writes:
> I think this is a good point (and welcome to the list!). It's not so
> much a problem in what we build into the AI, it's that "friendly" is
> a very loose concept. It's so loose that I doubt that it is really
> meaningful as a top-level goal. Such a goal would have to have a
> relatively precise definition, otherwise the AI will not be able to
> rigorously derive subgoals from it.
Apart from "friendly" being not a boolean metric, invariant all over
the place, whait is this "goal" thing?
It doesn't seem to be the standard AI meaning of goal, so I'd like to
hear the definition.
This archive was generated by hypermail 2b30 : Mon May 28 2001 - 09:50:14 MDT