Human Compatible
by Stuart Russell
The co-author of the standard AI textbook on why the standard model of AI, optimizing fixed objectives, is dangerous and how to build machines uncertain about human preferences. Clear and authoritative.
Read it if…
you want the AI-safety case from a leading researcher in plain language.
See the book →
Skip it if…
you want technical detail.
Try instead: Scary Smart →
Three things you will actually use
- Fixed objectives are the problem.
- Machines should be uncertain about what we want.
- Deference is safety.
Do this first
Read the chapter on the standard model and its flaw.
Our verdict
Authoritative and clear.
See the book →
Compare with other Character books
The Age of AI
Henry A. Kissinger, Eric Schmidt and Daniel Huttenlocher · Character
High-altitude overview.
CLICK TO SEE
Browse all Character book reviews or get the free Reality Code Cheat Sheet.
As an Amazon Associate, WisdomDeck earns from qualifying purchases. Links marked “Click to see” go to Amazon. We are not paid for opinions, prices and availability are not shown here and change on Amazon, and we never see your purchase details. Nothing here is medical, legal or financial advice.