How much control do you think we can have over AI individuality?
If we try to nudge the AI towards many individuals, e.g. Reduce AI Self-Allegiance by saying “he” instead of “I”, how likely do you think it’ll actually work?
How much control do you think we can have over AI individuality?
If we try to nudge the AI towards many individuals, e.g. Reduce AI Self-Allegiance by saying “he” instead of “I”, how likely do you think it’ll actually work?