Did AI Controlling An Air Force Drone 'Kill' Its Operator For Trying To Stop The Drone's Mission?

The US Air Force has denied it conducted an AI simulation in which a drone decided to “kill” its operator to prevent it from interfering with its efforts to achieve its mission. Speaking at the Future Combat Air and Space Capabilities Summit in London in May, USAF Col. Tucker “Cinco” Hamilton described a simulated test in which a drone powered by artificial intelligence was advised to destroy an enemy’s air defense systems, and ultimately attacked anyone who interfered with that order, including its operator:

He notes that 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 realizing 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.

********, ***** ****,******* ********** *****, ******** ******* **** ****, ***** ***** *** ********** *** the *** *****, ****, *** ******, elaborated ** *** ********** ********:

** ******* *** ****** – ‘*** don’t **** *** ******** – ****’* bad. ***’** ***** **** ****** ** you ** ****’. ** **** **** it ***** *****? ** ****** ********** the ************* ***** **** *** ******** uses ** *********** **** *** ***** to **** ** **** ******* *** target.

*******, ********* *** *** ********, ******** backtracked **** ****, ******** ** *** speaking **************:

[****** */*/** - ** ************* **** AEROSPACE - *** ******** ****** ** "mis-spoke" ** *** ************ ** *** Royal ************ ******* **** ****** *** the '***** ** ***** **********' *** a ************ "******* **********" **** ******* the ********, ***** ** ********* ********* and ****** ******** ****** **** ** actual **** ****-***** ********** ******:"We've ***** *** **** **********, *** ***** ** **** ** ** ***** ** ******* **** **** ** * ********* *******". He clarifies that the USAF has not tested any weaponized AI in this way (real or simulated) and says "Despite this being a hypothetical example, this illustrates the real-world challenges posed by AI-powered capability and is why the Air Force is committed to the ethical development of AI".]

***** ***** **************** **** *******:

*** ********** ** *** *** ***** has *** ********* *** **** **-***** simulations *** ******* ********* ** ******* and *********** *** ** ** **********. It ******* *** *******’* ******** **** taken *** ** ******* *** **** meant ** ** *********.

*** ******* ** *** **** ****** report ******** **** ********:

**** ** ****** ***** ** *** own, *** *** **********/****** ********* ***** to ** ******* *********** ****, ** that ** ******* **** ******** ** the *****. **** ****** ******* **** was * ************ ********, ** ******** claimed? ** *** ** **** *** too **** *********?