"[S]uch AIs might be good at certain kinds of sensing, thinking and planning but poor at understanding and reasoning about the ethical consequences of their actions. It is therefore important that we think carefully about AI safely as we build these more general-purpose systems, and put safety at the heart of the AIs operating system."
"AIs that are not transparent could behave in ways we don’t expect. By applying an understanding of how real brains control real bodies, we think these systems could be made more transparent, and we could advance towards having AIs that are better able to explain how they have made decisions," Prescott said.