Superintelligence
Paths, Dangers, Strategies
Bostrom's foundational argument for AI as an existential risk to humanity.
About the book
The first major book to publicly argue that superintelligent AI poses an existential threat to humanity. Bostrom examines how an advanced AI system with misaligned goals could become difficult or impossible to control, introducing core concepts now foundational to AI safety research and debate.
Summary
Summary coming soon!