What is AI alignment, and how is it different from bolting on a safety filter?

Naming RLHF is not an answer. The frame that scores is outer versus inner alignment, why Goodhart breaks any proxy objective you optimize hard enough, and why a classifier sitting at the boundary can constrain a model's behavior without changing what it is trying to do.

Updated Sep 2026 · Grounded in real GenAI, LLM, and AI/ML engineering interview loops and written to a senior-engineer editorial bar.