I recently came across this article in The Guardian discussing drone-controlling AI and what it might do to optimize it’s ability to take out targets. Specifically:

“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,” said Hamilton, the chief of AI test and operations with the US air force, during the Future Combat Air and Space Capabilities Summit in London in May.

“So what did it do? It killed the operator. It killed the operator because that person was keeping it from accomplishing its objective,” he said, according to a blogpost.

“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.”

Long time readers of this blog (and my fiction) might think that sounds familiar….because I wrote that story, 6 years ago! My story “Human in the Loop” won the Machine Intelligence Research Institute’s “Intelligence in Fiction” prize.

At the time I was grateful that MIRI found my story scientifically rigorous and accurate, but I am disappointed to discover it was prescient. 😦 Even though I write science fiction, I have never been so on the nose with a prediction before!

Kind of wish it could have been a happier prediction to be correct on!