References

The Alignment Problem; Machine Learning and Human Values

Brian Christian (2020)

W. W. Norton.

Abstract. Christian's accessible synthesis of AI-alignment research — bias, fairness, reward-hacking, inverse reinforcement learning, and the human-in-the-loop research program. The reference cited as the bridge between technical alignment research and AI-UX practice.

Tags: ai-usability alignment accessible

This site is currently in Beta. Contact: Chris Paton

Textbook of AI · Textbook of Digital Health

Auckland Maths and Science Tutoring