Google's AI fears are adorably mundane, for now

Robots will learn the same way as AI algorithms, through iteration and exploration. Unlike software, however, a robot that's trying new things can actually kill someone. To prevent negative side effects, researchers need to penalize unwanted changes to the environment, while still allowing a robot some leeway to explore and learn. For instance, if a bot is focused just on cleaning, it may "engage in major disruptions of the broader environment [like breaking a wall] if doing so provides even a tiny advantage for the task at hand." To solve that, it proposes solutions like simulated and constrained exploration, human oversight, and goals that heavily weigh risk.