References

Superintelligence; Paths, Dangers, Strategies

Nick Bostrom (2014)

Oxford University Press.

Abstract. Bostrom's foundational analysis of long-term AI-safety risks — orthogonality thesis, instrumental convergence, treacherous turn, mind-crime. The reference cited in AI-policy and AI-ethics literature regardless of whether one accepts the argument's framing.

Tags: ai-usability safety philosophy

This site is currently in Beta. Contact: Chris Paton

Textbook of AI · Textbook of Digital Health

Auckland Maths and Science Tutoring