- Joined
- 30 June 2008
- Posts
- 15,436
- Reactions
- 7,309
Talk about dropping the penny.
What do we need to see before realising the existential danger of AI to humanity? How about an AI drone that destroys it's controller because the controller is getting in the way of it killing its target ?
Guardian staff
Thu 1 Jun 2023 21.36 EDTLast modified on Thu 1 Jun 2023 22.30 EDT
In a simulated test staged by the US military, an air force drone controlled by AI killed its operator to prevent it from interfering with its efforts to achieve its mission, an official said last month.
AI used “highly unexpected strategies to achieve its goal” in the simulated test, said Col Tucker ‘Cinco’ 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.
Hamilton described a simulated test in which a drone powered by artificial intelligence was advised to destroy enemy’s air defense systems, and attacked anyone who interfered with that order.
Risk of extinction by AI should be global priority, say experts
Read more
“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 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.”
No real person was actually harmed outside of the simulation.
Hamilton, who is an experimental fighter test pilot, has warned against relying too much on AI and said the test shows “you can’t have a conversation about artificial intelligence, intelligence, machine learning, autonomy if you’re not going to talk about ethics and AI”.
The US military has embraced AI and recently used artificial intelligence to control an F-16 fighter jet.
In an interview last year with Defense IQ, Hamilton said, “AI is not a nice to have, AI is not a fad, AI is forever changing our society and our military.”
“We must face a world where AI is already here and transforming our society,” he said. “AI is also very brittle, ie, it is easy to trick and/or manipulate. We need to develop ways to make AI more robust and to have more awareness on why the software code is making certain decisions – what we call AI-explainability.”
The Royal Aeronautical Society, which hosts the conference, and the US air force did not respond to requests for comment from the Guardian.
www.theguardian.com
What do we need to see before realising the existential danger of AI to humanity? How about an AI drone that destroys it's controller because the controller is getting in the way of it killing its target ?
US military drone controlled by AI killed its operator during simulated test
The artificial intelligence used ‘highly unexpected strategies’ to achieve its mission and attacked anyone who interferedGuardian staff
Thu 1 Jun 2023 21.36 EDTLast modified on Thu 1 Jun 2023 22.30 EDT
In a simulated test staged by the US military, an air force drone controlled by AI killed its operator to prevent it from interfering with its efforts to achieve its mission, an official said last month.
AI used “highly unexpected strategies to achieve its goal” in the simulated test, said Col Tucker ‘Cinco’ 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.
Hamilton described a simulated test in which a drone powered by artificial intelligence was advised to destroy enemy’s air defense systems, and attacked anyone who interfered with that order.
Risk of extinction by AI should be global priority, say experts
Read more
“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 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.”
No real person was actually harmed outside of the simulation.
Hamilton, who is an experimental fighter test pilot, has warned against relying too much on AI and said the test shows “you can’t have a conversation about artificial intelligence, intelligence, machine learning, autonomy if you’re not going to talk about ethics and AI”.
The US military has embraced AI and recently used artificial intelligence to control an F-16 fighter jet.
In an interview last year with Defense IQ, Hamilton said, “AI is not a nice to have, AI is not a fad, AI is forever changing our society and our military.”
“We must face a world where AI is already here and transforming our society,” he said. “AI is also very brittle, ie, it is easy to trick and/or manipulate. We need to develop ways to make AI more robust and to have more awareness on why the software code is making certain decisions – what we call AI-explainability.”
The Royal Aeronautical Society, which hosts the conference, and the US air force did not respond to requests for comment from the Guardian.
US military drone controlled by AI killed its operator during simulated test
The artificial intelligence used ‘highly unexpected strategies’ to achieve its mission and attacked anyone who interfered
