“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.””
Google developing ‘kill switch’ to stop robot uprising against humans
http://www.telegraph.co.uk/technology/2016/06/08/google-developing-kill-switch-to-stop-robot-uprising-against-hum/
via Instapaper
Google developing ‘kill switch’ to stop robot uprising against humans
http://www.telegraph.co.uk/technology/2016/06/08/google-developing-kill-switch-to-stop-robot-uprising-against-hum/
via Instapaper