Contents
Dedication
Acknowledgements
Author Biography
Chapter 1. Introduction
Chapter 2. Unpredictability
Chapter 3. Unexplainability and Incomprehensibility
Chapter 4. Unverifiability
Chapter 5. Unownability
Chapter 6. Uncontrollability
Chapter 7. Pathways to Danger
Chapter 8. Accidents
Chapter 9. Personhood
Chapter 10. Consciousness
Chapter 11. Personal Universes
Chapter 12. Human ≠ AGI
Chapter 13. Skepticism
Biography
Dr. Roman V. Yampolskiy is a tenured associate professor in the department of Computer Engineering and Computer Science at the Speed School of Engineering, University of Louisville. He is the founding and current director of the Cyber Security Lab and an author of many books including Artificial Superintelligence: a Futuristic Approach. During his tenure at UofL, Dr. Yampolskiy has been recognized as: Distinguished Teaching Professor, Professor of the Year, Faculty Favorite, Top 4 Faculty, Leader in Engineering Education, Top 10 of Online College Professor of the Year, and Outstanding Early Career in Education award winner among many other honors and distinctions. Yampolskiy is a senior member of IEEE and AGI; member of the Kentucky Academy of Science, and he is a former research advisor for MIRI and associate of GCRI.
"This is a captivating and thought-provoking book about the most pressing issue of our time: should humanity risk committing collective suicide by rushing to build and unleash a new smarter-than-human species that we can neither understand nor control?" - Prof. Max Tegmark, MIT, author of Life 3.0
“Roman Yampolskiy’s AI: Unexplainable, Unpredictable, Uncontrollable is a compelling exploration of artificial intelligence's most troubling frontiers—where intelligence cannot be fully explained, behavior defies accurate prediction, and absolute control is out of reach. With clear and sometimes wry prose, Yampolskiy distills complex ideas into an accessible yet deeply insightful narrative. He provides both AI professionals and general readers with a captivating examination of risks that few openly acknowledge. A must-read for those who like their intelligence artificial but their warnings real.” - James Barrat, Author of Our Final Invention
“Roman V. Yampolskiy's extremely valuable book catalogues wide bodies of research which show that AI are inherently unpredictable and likely to become uncontrollable. It also helpfully lays out pre- and post-deployment pathways to dangerous outcomes. It is a must-read for anyone interested in AI safety--which, for reasons the book gives, should be every one of us.” -Marcus Arvan, Professor of Philosophy, University of Tampa
