Compatibility: how to control artificial intelligence. Russell S.

In the mass consciousness, superhuman artificial intelligence is a technological tsunami that threatens not only economics and human relations, but also civilization itself. The conflict between people and machines is seen inevitable, and its outcome is predetermined. Outstanding AI Stewart Russell, this scenario can be avoided. In his innovative book, the author tells how people have already learned to use AI, in the range from deadly autonomous weapons to manipulations by our preferences, and what else can teach him. If this happens and the superhuman AI appears, we will face an essence, much more powerful than ourselves. How to guarantee that a person will not be subordinate to the Superion?

, for this, Russell believes, artificial intelligence should be built on new principles. Machines should be modest and altruistic and solve our problems, and not their own. The reader learns about what kind of principles and how to realize them from this book, which the most authoritative publications in the world were called the main book about artificial intelligence.