News for hackers. Stuff that matters.

A comment on Gradual Disempowerment: How Even Incremental AI Progress Poses Existential Risks. Parent comment

Re:Gradual Disempowerment: How Even Incremental AI Progress ... by serviceberry on Saturday February 01, 2025 @12:05PM (#42899870)
AI has some approximation of the incentives of whoever trained it. Unless it's handed to us from above, I don't see how that would work.
[ Parent | on HN ]
Re:Gradual Disempowerment: How Even Incremental AI Progress ... by Saline9515 on Saturday February 01, 2025 @12:14PM (#42899966)
An AI has no hedonistic incentives such as the will to manipulate public procurement contracts to get kickbacks and buy itself a new SUV.
[ Parent | on HN ]