The Alignment Problem
Get The Book — Amazon, Opens in a new window. Other retailers & formats ↓About The Alignment Problem
Brian Christian explores the difficulty of aligning machine-learning systems with human intentions and values. Through researchers and practical problems, he examines what can go wrong when measurable objectives fail to capture what people actually care about.
Why I include it
Objectives, incentives, bias, and human judgment sit behind practical decisions about AI. The Alignment Problem connects everyday use with those deeper questions.
