$120,000 Token Bill for a 42-Hour AI Port, With a 96.22% Cache Hit Rate
martinwoodward · x · 2026-09-17
martinwoodward discloses the cost of the 42-hour migration: roughly $120,000 in tokens plus engineering time — not free, but a 96.22% input-token cache hit rate helped the economics, still orders of magnitude cheaper than similar efforts in the past. Also: 63% of team interactions were review/testing/CI and challenging decisions — agents wrote the code, engineering judgment didn't go away.
More from coding & agent
- Dev builds 3D universe explorer with 20 galaxies, 767 planets using Codex GPT-6.1 Sol — OpenAIDevs · 2026-11-02
- ChatGPT, Claude and Perplexity's fetchers don't run JavaScript, leaving client-rendered sites invisible to AI — gaganghotra_ · 2026-11-02
- SGLang boosts multimodal inference >10% by replacing GPU memory bookkeeping with a dict lookup — charles_irl · 2026-11-02
- kivi: hold Fn, talk, and it types polished text anywhere on your Mac — itsOmSarraf_ · 2026-11-02
- A base LLM plus 11 lines of code is all you need for a decision model — helloiamleonie · 2026-11-02
- Fix codebase structure before asking AI agents to write tests, says engineer — arpit_bhayani · 2026-11-02