Philosophies & Movements
AI Alignment
The more technical, narrower goal of ensuring an AI system’s actual behavior matches human intentions and values.
Origin · no single documented coiner
Grew out of Eliezer Yudkowsky’s (profiled on our Who’s Who page) earlier “Friendly AI” concept and was developed further through the 2010s by researchers including Stuart Russell (UC Berkeley) and Paul Christiano.
No single primary source link for this term.
