Google’s AI Team Deep Mind Developing a ‘Safe Interruptibility/Kill Switch’ for Robots

Published by , June 6, 2016 4:51 am
(DailyStar) Google has published a paper outlining the work its British artificial intelligence team Deep Mind is doing to develop a “kill switch” to ensure the survival of the human race. Deep Mind create algorithms which allow robots to learn from raw experience or data. But now the team are developing “safe interruptibility”, a way to stop robots from learning how to prevent humans from stopping an activity.
“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,” the team wrote.
Tags: , , ,