News for hackers. Stuff that matters.
Re:Artificial intelligence risk research by joe_the_user on Saturday December 12, 2015 @06:31PM (#10724656)
We unintentionally produce programs while fail or produce small variations on their original purpose - give control to X person rather than Y person.

We haven't unintentionally produced a program that had a whole range of unexpected behaviors. An intelligence having human-like "survival instincts" and etc would be a big variation on a tool.

There are no comments on this comment yet.