Your AI Patch Is Cheap to Write and Expensive to Review: A 90-Minute Review-Cost Ledger
Описание и применение
Проблема: AI‑плагины снижают затраты на написание кода, но увеличивают время ручного ревью. Решение: 90‑минутный спайк с скриптом review_ledger.py, измеряющим время ревью и сравнивающим его с ручными патчами.
Задача
AI-generated patches reduce coding effort but increase human review time, making software still expensive.
Результат
The spike produced a lightweight, stdlib‑only tool that measures whether AI patches increase review time beyond a 50% median increase compared to hand‑written patches.
Рабочий процесс
- Write hypothesis and kill rule (0–10 min)
- Build ledger script review_ledger.py (10–25 min)
- Run five fixed tasks and generate patches (25–60 min)
- Time each review and record minutes (60–80 min)
- Compute median review minutes, compare ratio, and produce verdict (80–90 min)
Доказательства
Agent patches that pass CI cost no more human review minutes than hand‑written patches touching the same files.
Three numbers, not a dashboard
The spike is not about which model is best. It is about whether your review loop absorbs the output at a sane price.
- Дата записи: 2026-10-26T13:11:11.575Z