Google is currently working on a “kill switch” for the the terrifying possibility that the world’s robots and algorithms stop listening to us.
Google’s Deep Mind team recently published a paper, detailing its work and how it would stop “a Skynet scenario” from happening.
The framework revolves around an AI from learning how to prevent – or induce – human interruption of whatever it’s doing.
“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 necessarily receive rewards for this”.
More gaming news
Fan remake of Star Wars: Battlefront 3 coming to Steam for free
This is how game prices hit R1,000 in South Africa: 1998–2016
Why we should scrap ‘dumb passwords’ in favour of smarter security
Loading ...
