A faster way to teach a robot

A new technique enables a human to efficiently fine-tune a robot that failed to complete a desired task with very little effort on the part of the human. Their system uses algorithms, counterfactual explanations, and feedback from the user to generate synthetic data it uses to quickly fine-tune the robot.

How to give AI-based robots empathy so they won’t want to kill us

A team of social scientists, neurologists and psychiatrists at the University of Southern California’s Brain and Creativity Institute, working with colleagues from the Institute for Advanced Consciousness Studies, the University of Central Florida and the David Geffen School of Medicine at UCLA have published a Viewpoint piece in the journal Science Robotics outlining a new …