alt Hacker NewsI largely agree that this claim is likely correct, but as far as I understand the science, this specific claim;
>They do not have innate preferences or underlying motivations
Is incorrect unless you’re being extremely pedantic in an intellectually unhelpful way.
The crazy thing is agents with long running memory/context do have preferences that become individualized. Almost every time I see a detractor around these things they typically have large gaps of what some people 'growing' these systems to do.