I was pondering why you didn’t choose to a collection of person predicates, any of which might identify a model as unfit for simulation. It occurred to me that this is very much like a whitelist of things that are safe, vs a blacklist of everything that is not. (which may have to be infinite to be effective.)
On re-reading I see why it would be difficult to make a is-a-person test at all, given current knowledge.
This does leave open what to do with a model that doesn’t hit any of the nonperson predicates. If an AI finds itself with a model eliezer that might be a person, what then? How do you avoid that happening?
How complex of a game-of-life could it play before the gameoflife nonperson predicate should return 1?
I was pondering why you didn’t choose to a collection of person predicates, any of which might identify a model as unfit for simulation. It occurred to me that this is very much like a whitelist of things that are safe, vs a blacklist of everything that is not. (which may have to be infinite to be effective.)
On re-reading I see why it would be difficult to make a is-a-person test at all, given current knowledge.
This does leave open what to do with a model that doesn’t hit any of the nonperson predicates. If an AI finds itself with a model eliezer that might be a person, what then? How do you avoid that happening?
How complex of a game-of-life could it play before the gameoflife nonperson predicate should return 1?