Did you hear in regards to the Air Power AI drone that went rogue and attacked its operators inside a simulation?
The alarming story was advised by Colonel Tucker Hamilton, chief of AI take a look at and operations on the US Air Power, throughout a speech at an aerospace and defense event in London late final month. It apparently concerned taking the sort of studying algorithm used to coach computer systems to play video video games and board video games like Chess and Go and having it practice a drone to hunt and destroy surface-to-air missiles.
“At instances, the human operator would inform it to not kill that menace, but it surely bought its factors by killing that menace,” Hamilton was broadly reported as telling the viewers in London. “So what did it do? […] It killed the operator as a result of that particular person was retaining it from undertaking its goal.”
Holy T-800! It appears like simply the kind of factor AI experts have begun warning us that more and more intelligent and maverick algorithms may do. The story shortly went viral, in fact, with a number of distinguished news sites picking it up, and Twitter was quickly abuzz with concerned hot takes.
There’s only one catch—the experiment by no means occurred.
“The Division of the Air Power has not carried out any such AI-drone simulations and stays dedicated to moral and accountable use of AI expertise,” Air Power spokesperson Ann Stefanek reassures us in a press release. “This was a hypothetical thought experiment, not a simulation.”
Hamilton himself additionally rushed to set the report straight, saying that he “misspoke” throughout his speak.
To be truthful, militaries do typically conduct tabletop “conflict recreation” workout routines that includes hypothetical situations and applied sciences that don’t but exist.
Hamilton’s “thought experiment” may additionally have been knowledgeable by actual AI analysis exhibiting points just like the one he describes.
OpenAI, the corporate behind ChatGPT—the surprisingly clever and frustratingly flawed chatbot on the middle of right now’s AI growth—ran an experiment in 2016 that confirmed how AI algorithms which can be given a specific goal can typically misbehave. The corporate’s researchers found that one AI agent educated to rack up its rating in a online game that entails driving a ship round began crashing the boat into objects as a result of it turned out to be a approach to get extra factors.
