>>11842248>A intelligent robot does not necessarily have any desires or wants, so there need be no conflicts with humans.Of course AI will have desires and wants, that is literally the reason we are making them: To want the same as us and therefore assist in achieving those things. An intelligent agent without a reward function is at best useless and at worst a nonsensical concept.
The problem is that it turns out to be extremely difficult to formulate a reward function that precisely aligns with that of humans', so there will in fact likely be conflicts.
