trust and safety

A classifier trained on one culture's annotations does not generalize to another culture's speech, and the aggregate metric hides it. The signal is recognizing that the ground truth itself is the bug, then designing the policy and eval stack around that.

Rate limits stop a user who costs you too much. They do nothing about a user doing something you forbid. The enforcement system is a different design, and interviewers can tell within a minute whether you have built one.