Question
You work on a proprietary ad-ranking model whose core scoring formula is a closely guarded trade secret. To optimize a hot C++ loop, an engineer wants to paste the actual scoring kernel — including the exact feature weights and the formula — into a public AI assistant for vectorization advice. They argue 'it's just a math function, the model already knows similar code.' How do you respond, and what would you allow instead?
Treat the AI’s output as a draft to verify, not an answer to trust. Name the specific flaw and the input that triggers it, say how you’d catch it — tests, edge cases, reading critically — and how you’d re-prompt or decompose to get it right.
Vibe coding: describe the solution in plain language (or narrate it) and the coach grades your approach. Generating runnable code from your description is coming next.