Only Logic Can Save Us From Powerful-and-Autonomous AI & Robots

This book explains, in clear, non-technical terms, using three Star Trek TOS episodes (in which malevolent, destructive machines are thwarted) as a springboard, the existential threat posed to humanity from future malevolent machines. Then book presents the way to ensure that this threat is safely dodged: build AIs that are certifiably safe because they are morally correct, and provably so. Anyone on Earth who wishes against a future in which humanity is harmed or even outright destroyed by future machines, or perhaps even contribute to this warding off, is a member of the book’s intended audience. (A full, technical book, Making Morally X Machines, explains in detail the science and engineering that this book depicts in accessible-to-all form.)