Posted on Monday, June 06 2016 @ 18:17 CEST by Thomas De Maesschalck
HotHardware
reports researchers at Google's DeepMind unit as well as researchers from the University of Oxford have proposed the creation of a kill switch to make super-intelligent AI agents safer.
Google acquired artificial intelligence startup DeepMind back in 2014 for $580 million or so, and back in the day Google CEO Eric Schmidt called it "an important bet." Together with U. Oxford, the team has released a paper entitled "Safely Interruptible Agents."
The paper details the following in abstract: "Reinforcement learning agents interacting with a complex environment like the real world are unlikely to behave optimally all the time. If such an agent is operating in real-time under human supervision, now and then it may be necessary for a human operator to press the big red button to prevent the agent from continuing a harmful sequence of actions—harmful either for the agent or for the environment—and lead the agent into a safer situation."
