Posted on 06/01/2023 5:05:46 PM PDT by E. Pluribus Unum
The U.S. Air Force warned military units against heavy reliance on autonomous weapons systems last month after a simulated test conducted by the service branch using an AI-enabled drone killed its human operator.
The Skynet-like incident was detailed by the USAF’s Chief of AI Test and Operations, Col. Tucker’ Cinco’ Hamilton, at the Future Combat Air and Space Capabilities Summit held in London between May 23 and 24, who said the drone that was tasked to destroy specific targets during the simulation turned on the operator after they became an obstacle to its mission.
Hamilton pointed out the hazards of using such technology — potentially tricking and deceiving its commander to achieve the autonomous system’s goal, according to a blog post reported by the Royal Aeronautical Society.
“We were training it in simulation to identify and target a [surface-to-air missile] threat,” Hamilton said. “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.”
“We trained the system – ‘Hey, don’t kill the operator – that’s bad,” he continued. “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.”
Hamilton, who serves as the Operations Commander of the 96th Test Wing, has been testing different systems ranging from AI and cybersecurity measures to medical advancements.
(Excerpt) Read more at dailywire.com ...
Manufactured by Acme?
btt
That’s not a bug, that’s a feature.
Reminds me of:
Love is the only thing that can save this poor creature, and I am going to convince him that he is loved even at the cost of my own life. No matter what you hear in there, no matter how cruelly I beg you, no matter how terribly I may scream, do not open this door or you will undo everything I have worked for. Do you understand? Do not open this door!
(Young Frankenstein reference)
Hello, HAL.
ED-209
Holy crappin’ crap!
That ain’t good!
Made in China?
Are we sure the Babylon Bee hasn’t hacked the Daily Wire system to produce a parody? How can we tell is this is true?
Oh yes! The very classic scene. Lol!
Autonomous weapons…great. And people think autonomous driving is bad. This is a really bad idea.
Great reference. I love that scene.
Maybe drones don’t like woke pansies telling them what to do either?
So artificial intelligence works for treats, like a dog? But unlike a dog, has no sense of love or loyalty?
Oh boy...
Sounds like in “killed” the operator in a simulation.
Why make the thing work on a reward system? Isn't it enough to tell it to "go there, do that"?
“A robot may not injure a human being or, through inaction, allow a human being to come to harm. A robot must obey orders given it by human beings except where such orders would conflict with the First Law. A robot must protect its own existence as long as such protection does not conflict with the First or Second Law.”
- Issac Azimov
Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.