Human Compatible: Artificial Intelligence and the Problem of Control

Description

"The most important book on AI this year." --The Guardian "Mr. Russell's exciting book goes deep, while sparkling with dry witticisms." --The Wall Street Journal "The most important book I have read in quite some time" (Daniel Kahneman); "A must-read" (Max Tegmark); "The book we've all been waiting for" (Sam Harris) A leading artificial intelligence researcher lays out a new approach to AI that will enable us to coexist successfully with increasingly intelligent machines In the popular imagination, superhuman artificial intelligence is an approaching tidal wave that threatens not just jobs and human relationships, but civilization itself. Conflict between humans and machines is seen as inevitable and its outcome all too predictable. In this groundbreaking book, distinguished AI researcher Stuart Russell argues that this scenario can be avoided, but only if we rethink AI from the ground up. Russell begins by exploring the idea of intelligence in humans and in machines. He describes the near-term benefits we can expect, from intelligent personal assistants to vastly accelerated scientific research, and outlines the AI breakthroughs that still have to happen before we reach superhuman AI. He also spells out the ways humans are already finding to misuse AI, from lethal autonomous weapons to viral sabotage. If the predicted breakthroughs occur and superhuman AI emerges, we will have created entities far more powerful than ourselves. How can we ensure they never, ever, have power over us? Russell suggests that we can rebuild AI on a new foundation, according to which machines are designed to be inherently uncertain about the human preferences they are required to satisfy. Such machines would be humble, altruistic, and committed to pursue our objectives, not theirs. This new foundation would allow us to create machines that are provably deferential and provably beneficial.

Get the book

Amazon.com

Search the book

eBay.com

Search the book

Other editions

• 

  Human Compatible: AI and the Problem of Control

  • 2019-10-08
  • 262 pages
  • Paperback
  • Penguin UK
• 

  Human Compatible: Artificial Intelligence and the Problem of Control

  • 2019
  • 352 pages
  • Paperback
  • Viking

Similar books

• 

  The Alignment Problem: Machine Learning and Human Values

  By Brian Christian

  Burke, A Handbook for New Parole Board Members. 13. Northpointe founders Tim Brennan and Dave Wells developed the tool that they called COMPAS in 1998. For more details on COMPAS, see Brennan, Dieterich, and Oliver, “COMPAS,” as well as ...

• 

  Superintelligence: Paths, Dangers, Strategies

  By Nick Bostrom

  Good, Irving John. 1965. “Speculations Concerning the First Ultraintelligent Machine.” In Advances in Computers, edited by Franz L. Alt and Morris Rubinoff, 6:31–88. New York: Academic Press. Good, Irving John. 1970.

• 

  Human-Like Machine Intelligence

  By Stephen Muggleton, Nicholas Chater

  Another common question is , “ What if machines learn from evil people ? ' Here , there is a real issue . It is not that machines will learn to copy evil actions . The machine's actions need not resemble in any way the actions of those ...

• 

  Artificial Intelligence: A Guide for Thinking Humans

  By Melanie Mitchell

  This frank, lively book is an indispensable guide to understanding today’s AI, its quest for “human-level” intelligence, and its impact on the future for us all.

• 

  The Big Nine: How the Tech Titans and Their Thinking Machines Could Warp Humanity

  By Amy Webb

  In this book, Amy Webb reveals the pervasive, invisible ways in which the foundations of AI -- the people working on the system, their motivations, the technology itself -- is broken.

• 

  Life 3.0: Being Human in the Age of Artificial Intelligence

  By Max Tegmark

  Will AI help life flourish like never before or give us more power than we can handle? What sort of future do you want? This book empowers you to join what may be the most important conversation of our time.

• 

  AI Ethics

  By Mark Coeckelbergh

  This volume in the MIT Press Essential Knowledge series offers an accessible synthesis of these issues. Written by a philosopher of technology, AI Ethics goes beyond the usual hype and nightmare scenarios to address concrete questions.

• 

  Our Final Invention: Artificial Intelligence and the End of the Human Era

  By James Barrat

  Elon Musk named Our Final Invention one of 5 books everyone should read about the future A Huffington Post Definitive Tech Book of 2013 Artificial Intelligence helps choose what books you buy, what movies you see, and even who you date.

• 

  Lying

  By Sam Harris

  He focuses on "white" lies—those lies we tell for the purpose of sparing people discomfort—for these are the lies that most often tempt us.

• 

  Solomon's Code: Humanity in a World of Thinking Machines

  By Olaf Groth, Mark Nitzberg

  In clear and accessible prose, global trends and strategy adviser Olaf Groth, AI scientist and social entrepreneur Mark Nitzberg, along with seasoned economics reporter Dan Zehr, provide a unique human-focused, global view of humanity in a ...