Vetted AI code is hard to justify

A developer reports that using a frontier coding agent to build a large optimization for his game took several days of planning, a week to review the massive diff, and another week to refactor, leaving him burned out, whereas building it unassisted would have taken about a month but with slower burnout. The developer, who reviewed and approved every line, now questions the justification for vetted AI-generated code.

Vetted AI code is hard to justify I have been reflecting on a large optimization I built for my game https://x.com/GetLostTheGame/status/2087864598804525248 with the assistance of a frontier coding agent. This optimization took me several days to plan with the agent, about a week to comprehend the massive diff it produced I review and approve every line , and another week to refactor and refine it until completion. By the end, I understood everything that had been built—as if I had written it myself—but I was burned out. Untangling and comprehending large amounts of clever, high performance code and deciding if it makes sense within each stratum of abstraction is taxing on the mind. If I had built it entirely unassisted, I suspect it would have taken me about a month. It would have been difficult, but I would have paid the comprehension costs as I developed it, in manageable chunks, and burned out much more slowly. I asked Claude make me an interactive visualization for how I perceive these relationships of coding, comprehension, and burnout: