Iason Gabriel (2020)
Minds and Machines, 30(3), 411-437.
DOI: https://doi.org/10.1007/s11023-020-09539-2
Abstract. Gabriel's foundational philosophical analysis of AI value alignment — distinguishing instruction-following, intention- alignment, preference-alignment, interest-alignment, and value- alignment. The reference cited in technical-philosophical AI- alignment literature.
Tags: ai-usability alignment philosophy