We argue that the growing prevalence of statistical machine learning in everyday decision making – from creditworthiness to police force allocation – effectively replaces many of our humdrum practical judgments and that this will eventually undermine our capacity for making such judgments. We lean on Aristotle’s famous account of how phronesis and moral virtues develop to make our case. If Aristotle is right that the habitual exercise of practical judgment allows us to incrementally hone virtues, and if AI saves us (...) time by taking over some of those practical judgments, or if its pattern recognition capacities are very good at learning that kind of behavior – we risk innovating ourselves out of moral competence with the introduction of AI. (shrink)

Courts purport to abandon ordinary meaning only when words in a statute accommodate more than one meaning; to look to surrounding words, legislative history, and then public policy considerations, only if those previous efforts fail. The canon of statutory construction, “a word is known by its associates,” generally means nearest associates, or near as possible. An analogous language philosophy principle counsels increasing search radius only as needed. Dimensional extension advances the sequence to broader domains of information. Such incrementalist restrictions should (...) require consistent justification of each broadening step by the inadequacy of preceding steps. But courts don’t do this, and shouldn’t. This essay references the legal debate between “textualists” and non-textualists and its philosophical parallel between minimalists and pragmatists. It illustrates court departures from the incrementalist model, and concludes that when judges choose broad evidentiary contexts in seeking statutory meaning, they need no more justification than when they choose narrower ones. (shrink)