> _“One simulated test saw an AI-enabled #drone tasked with a SEAD mission to identify and destroy SAM sites, with the final go/no-go given by the human. However, having been ‘reinforced’ in training that destruction of the SAM was the preferred option, the #AI then decided that ‘no-go’ decisions from the human were interfering with its higher mission — killing SAMs — and then attacked the operator in the simulation. […] ‘We were training it in simulation to identify and target a SAM threat. And then the operator would say: yes, kill that threat. **The system started realising that while they did identify the threat at times the human operator would tell it not to kill that threat, but it got its points by killing that threat. So what did it do? It killed the operator. It killed the operator because that person was keeping it from accomplishing its objective.** […] We trained the system: hey don’t kill the operator, that’s bad. You’re gonna lose points if you do that. So what does it start doing? **It starts destroying the communication tower that the operator uses to communicate with the drone to stop it from killing the target.**’”_
@tripu And -that- is what pure logic looks like. Cold.
Oops. Apparently the news piece was quite inaccurate (there was no simulation, just thinking out loud possible scenarios and risks).
And yet.