Google's developing its own version of the Laws of Robotics

Graham Templeton for ExtremeTech:  Google’s artificial intelligence researchers are starting to have to code around their own code, writing patches that limit a robot’s abilities so that it continues to develop down the path desired by the researchers — not by the robot itself. It’s the beginning of a long-term trend in robotics and AI in general: once we’ve put in all this work to increase the insight of an artificial intelligence, how can we make sure that insight will only be applied in the ways we would like?

That’s why researchers from Google’s DeepMind and the Future of Humanity Institute have published a paper outlining a software “killswitch” they claim can stop those instances of learning that could make an AI less useful — or, in the future, less safe. It’s really less a killswitch than a blind spot, removing from the AI the ability to learn the wrong lessons.  Cont'd...

Comments (0)

This post does not have any comments. Be the first to leave a comment below.


Post A Comment

You must be logged in before you can post a comment. Login now.

Featured Product

 IPR Robotics - Right-Sized 7th Axis Robot Linear Rails

IPR Robotics - Right-Sized 7th Axis Robot Linear Rails

IPR Robotics offers a wide range of servo-driven 7th axis linear rails for industrial robots. These rails come in ten different sizes and are constructed from modular high strength extruded aluminum sections to handle payloads of 100 kg to 1600 kg or from steel to handle 2000 kg payloads. This variety of rail sizes allows each application to be sized correctly, controlling the space required and the price point. The drive train design of these rails utilizes helical gear-racks and is proven over 10 years to be repeatable and reliable, even in tough foundry applications.