Report: USAF experimental drone simulation AI turned on human operator

This was just in a simulation but how the hell can the programming allow the system to prioritize winning the mission over preserving the human directive? That’s like AI programming 101 isn’t it?

Sounds to me that either part of the simulation was to make the drone attack the operator in a given scenario, or the target recognition code needs some work. In any case, this is the type of crap that makes people believe AI thinks by itself and makes its own decisions.