News for hackers. Stuff that matters.
Re:Some documents on AM and EURISKO by khafra on Thursday November 15, 2018 @09:23AM (#18459403)
It's not just cute, it's an open problem in the theory of recursively self-modifying AI design--there's no general solution to an AI hijacking its own reward channel, so far. https://www.lesswrong.com/posts/upLot6eG8cbXdKiFS/reward-fun... is the most recent thing I know of in the area.

There are no comments on this comment yet.