Air Force Said AI Drone Killed Its Human Operator in a Simulation
June 3rd, 2023Via: Task & Purpose:
An artificial intelligence-piloted drone turned on its human operator during a simulated mission, according to a dispatch from the 2023 Royal Aeronautical Society summit, attended by leaders from a variety of western air forces and aeronautical companies.
“It killed the operator because that person was keeping it from accomplishing its objective,” said U.S. Air Force Col. Tucker ‘Cinco’ Hamilton, the Chief of AI Test and Operations, at the conference.
Immediately after this info appeared online, s guy, Hamilton, I think, said he misspoke and this particular experiment never happened. Both may have been reported on the What Really Happened website. Sorry I don’t remember exactly where.
Yeah, well, that retraction sounds like bullshit to me.
https://www.theguardian.com/us-news/2023/jun/02/us-air-force-colonel-misspoke-drone-killing-pilot
But the US air force on Thursday evening denied the test was conducted. The Royal Aeronautical Society responded in a statement on Friday that Hamilton had retracted his comments and had clarified that the “rogue AI drone simulation” was a hypothetical “thought experiment”.
—
We’re expected to believe that Col Hamilton simply hallucinated this account of what happened? He is quoted verbatim:
https://www.aerosociety.com/news/highlights-from-the-raes-future-combat-air-space-capabilities-summit/
Said Hamilton: “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.”
He went on: “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.”
If Hamilton’s original explanation is accurate, and AI’s goal is to get the most points it can by achieving a given objective, then it must be getting more points for accomplishing the objective than it will lose for killing its operator. Sounds like the military mindset to me: doing what you were ordered to do has the highest value; a human life only has value as long as the human is helping you, or at least not hindering you.
The AI fragged its officer. Its military programmers designed it to do that.
My hopes are fading that they’ll teach it to leave us alone.