Google: How do we build a cleaning robot that doesn't cheat or destroy things in its path? ZDNet

Google earlier this year revealed it's been using machine learning to teach a group of robotic arms to grasp household objects. Google says it wants to bring "precision" to the debate about safety and artificial intelligence (AI), which has often veered into discussions about smarter machines stealing jobs or even rising up and destroying humanity. Scientists from Google's deep-learning research unit, Google Brain, the Elon Musk-backed OpenAI, and Stanford and Berkeley universities, have teamed up to explore five safety problems that could arise as AI is applied to general systems for the home, office, and industry. "While possible AI safety risks have received a lot of public attention, most previous discussion has been very hypothetical and speculative. We believe it's essential to ground concerns in real machine-learning research, and to start developing practical approaches for engineering AI systems that operate safely and reliably," wrote Chris Olah, one of the Google Brain contributors to the paper.