‘The most significant book on AI this year.’ –The Guardian

‘Mr. Russell’s fascinating book goes deep, while gleaming with dry witticisms.’ –The Wall Street Journal

‘The most important book I’ve read in quite some period’ (Daniel Kahneman); ‘A must-read’ (Utmost Tegmark); ‘The publication we’ve all been waiting around for’ (Sam Harris)

A leading artificial intelligence researcher lays out a new approach to AI that will allow us to coexist successfully with increasingly intelligent devices

In the popular about Human Compatible: Artificial Intelligence as well as the Problem of Control imagination, superhuman artificial intelligence can be an approaching tidal wave that threatens not just jobs and human relationships, but civilization itself. Turmoil between humans and machines sometimes appears as inevitable and its outcome all too predictable.

Within this groundbreaking book, distinguished AI researcher Stuart Russell argues that this scenario could be avoided, but only if we rethink AI from the ground up. Russell starts by exploring the idea of cleverness in humans and in devices. He explains the near-term benefits we can expect, from intelligent personal assistants to vastly accelerated scientific research, and outlines the AI breakthroughs that still need to happen before we reach superhuman AI. He also spells out the methods humans are already finding to misuse AI, from lethal autonomous weapons to viral sabotage.

If the predicted breakthroughs occur and superhuman AI emerges, we could have created entities far more powerful than ourselves. How do we guarantee they never, ever, possess power over us? Russell suggests that we can restore AI on a fresh foundation, according to which machines are designed to become inherently uncertain about the individual preferences they must satisfy. Such devices would be humble, altruistic, and committed to pursue our goals, not really theirs. This new foundation would allow us to produce machines that are provably deferential and provably helpful.