News for hackers. Stuff that matters.

A comment on Having AI systems try to outwit one another could help judge their intentions. Parent comment

Re:Having AI systems try to outwit one another could help ju... by rainieri on Friday May 04, 2018 @12:12PM (#16995704)
Exactly. One AI programmed with bad intentions will have bad intentions. One with good will do good as programmed. Which one outwits the other will simply result in a part of the code that has a programmed advantage over the other.
[ Parent | on HN ]

There are no comments on this comment yet.