From my perspective, this is worth thinking about since it’s a scenario that may arise even in the happy case where we solve the more immediate existential AI risks. The point of the work is to show that as soon as you start considering granting moral status to AIs, moral hijacking becomes an immediate corollary.
From my perspective, this is worth thinking about since it’s a scenario that may arise even in the happy case where we solve the more immediate existential AI risks. The point of the work is to show that as soon as you start considering granting moral status to AIs, moral hijacking becomes an immediate corollary.