Read more
Thos book is a comprehensive and interdisciplinary introduction to AI Safety. As AI threatens to transform society, it becomes increasingly more important to understand the risks that AI poses, and to learn what measures we can take to mitigate them.
List of contents
Introduction
Section I AI and Societal-Scale Risks
Chapter 01 Overview of Catastrophic AI Risks
Chapter 02 Artificial Intelligence Fundamentals
Section II Safety
Chapter 03 Single-Agent Safety
Chapter 04 Safety Engineering
Chapter 05 Complex Systems
Section III Ethics and Society
Chapter 06 Beneficial AI and Machine Ethics
Chapter 07 Collective Action Problems
Chapter 08 Governance
Acknowledgements
References
About the author
Dr. Dan Hendrycks is a machine learning researcher and Director of the Center for AI Safety (CAIS), USA. Dan holds a Ph.D. in Machine Learning from UC Berkeley. Dr. Hendrycks has given dozens of accessible and engaging talks on AI safety to diverse audiences at institutions such as OpenAI, Google, and Stanford. His expertise is regularly sought, evidenced by his role in organizing AI safety-related workshops at prestigious conferences, including NeurIPS, ICML, and ECCV. His work has not only had a substantial impact on the academic community but has also gained considerable public attention. Dr. Hendrycks has been profiled in media outlets like the Boston Globe and has had his work featured in the BBC, New York Times, TIME Magazine, and Washington Post.
Summary
Thos book is a comprehensive and interdisciplinary introduction to AI Safety. As AI threatens to transform society, it becomes increasingly more important to understand the risks that AI poses, and to learn what measures we can take to mitigate them.
