The rise of the robots could be a genuine threat to the human race, experts have warned, but Google hope to find a way of stopping Artificial Intelligence (AI) from taking over the world.
Developers from the search engine’s artificial intelligence division, DeepMind, have teamed up with Oxford University of science and technology to develop a program called ‘kill switch’ for AI.
Google’s Laurent Orseau and Stuart Armstrong, from the Future of Humanity Institute, say it may be necessary for humans to press a “big red button” to stop AI from carrying out a “harmful sequence of actions”.
“If 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,” the media report.
They referenced a robot that learned how to pause a game of Tetris to avoid losing, adding that AIs are “unlikely to behave optimally all the time”.
“We have proposed a framework to allow a human operator to repeatedly safely interrupt a reinforcement learning agent while making sure the agent will not learn to prevent or induce these interruptions,
Safe interruptibility can be useful to take control of a robot that is misbehaving and may lead to irreversible consequences, or to take it out of a delicate situation, or even to temporarily use it to achieve a task it did not learn to perform or would not normally receive rewards for this.”
No comments:
Post a Comment
Comments