Google’s brightest minds are working on a big red button (kill switch) to disable rogue AI systems that want to take over the world.
With most tech companies punting their advancements in artificial intelligence through their virtual assistants there is deferentially a philosophical case to make with regards to where the line is going to be drawn. What if AI suddenly decided it knew better than we did and started making decisions of its own? Somehow these hypothetical situations never seem to end well.
With that in mind Google is working n an AI ‘kill switch’ that allows human operators to turn off super intelligent systems no matter how big their egos get. It’s called “safe interruptibility” and it’s being developed as part of the DeepMind system that recently proved its prowess at Go. The DeepMind team has published a paper on the topic that details how this “kill switch” will be built.
The paper’s authors, Laurent Orseau and Stuart Armstrong stated – “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 key fail-safe to build into this “kill switch” feature is the prevention of the AI to circumvent the deactivation. Researchers also admit that scheduled interruptions, which machines can anticipate, may be more difficult to impose. It will be intersting to see what the future holds and how researchers will approach this issue. the future will be with us sooner rather than later so I for one am happy that Google’s brightest minds are already hard at work.
Source: TechRadar Follow Jaco on Twitter:@Jaco_vdWalt