Artificial superintelligence : a futuristic approach / Roman V. Yampolskiy, University of Louisville, Kentucky, USA.

AI-completeness: the problem domain of superintelligent machines
The space of mind designs and the human mental model
How to prove you invented superintelligence so no one else can steal it
Wireheading, addiction, and mental illness in machines
On the limits of recursively self-improving artificially intelligent systems
Singularity paradox and what to do about it
Superintelligence safety engineering
Artificial intelligence confinement problem (and solution)
Efficiency theory: a unifying theory for information, computation, and intelligence
Controlling the impact of future superintelligence.