Human Compatible: Artificial Intelligence and the Problem of Control"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. |
What people are saying - Write a review
We haven't found any reviews in the usual places.
Contents
| 1 | |
| 7 | |
| 13 | |
How MIGHT AI PROGRESS IN THE FUTURE2 | 62 |
NAISUSES OF AI | 103 |
OVERLY INTELLIGENT Al | 132 |
THE NOTSOGREAT AI DEBATE | 145 |
A DIFFERENT APPROACH | 171 |
US | 211 |
PROBLENA SOLVED? | 246 |
SEARCHING FOR SOLUTIONS | 257 |
KNOWLEDGE AND LOGIC | 267 |
UNCERTAINTY AND PROBABILITY | 273 |
LEARNING FRONT EXPERIENCE | 285 |
Acknowledgments | 297 |
Image Credits | 324 |
Other editions - View all
Human Compatible: Artificial Intelligence and the Problem of Control Stuart Russell Limited preview - 2019 |
Human Compatible: Artificial Intelligence and the Problem of Control Stuart Russell No preview available - 2020 |
Common terms and phrases
able achieve actions agent algorithm Alice allow already answer applications Artificial Intelligence become begin behavior better brain build called choices complex concern consider course create decision deep described develop economic effect example expected experience fact figure future give given goal hand happen Harriet human hundred idea important individual intelligence it's kind knowledge lead learning less lives logic machines means methods million moral move networks objective observable perhaps person physical play position possible predict preferences probability problem produce proposed question rational reasoning require result reward risks Robbie robot rules seems sense simple solution steps superintelligent tasks theory things thousands tion true turn uncertainty understand University utility
Bibliographic information
| Title | Human Compatible: Artificial Intelligence and the Problem of Control |
| Author | Stuart Russell |
| Publisher | Penguin, 2019 |
| ISBN | 0525558624, 9780525558620 |
| Length | 352 pages |
| Subjects | › › Business & Economics / Industries / Computers & Information Technology Science / Biotechnology Technology & Engineering / Robotics |
| Export Citation | BiBTeX EndNote RefMan |