Streaming statistics numerics spec
You're directing an AI agent to write a Go function that computes a running average and standard deviation over a stream of millions of float64 sensor readings, for an analytics pipeline. Write the prompt/spec that makes it numerically robust at scale. What algorithm and precision constraints do you mandate, and what acceptance criteria catch the failure? Then state what a naive prompt ('compute mean and stddev of the stream') produces that's wrong on real data.
welford_running_stats(readings: list[float]) → list[float][[2,4,4,4,5,5,7,9]]out[5,4,2][[]]out[0,0,0]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 & agentic: describe the solution in plain language (or narrate it) and the coach grades your approach.