Implementation That Favors the AI, Review That Favors the Human---Writing a COW Filesystem from Scratch, Part 2
Описание и применение
Автор внедрил многопартийный процесс проверки, где главный агент распределяет задачи между сильным, поддерживающим и атакующим агентами, чтобы минимизировать ошибки и галлюцинации при проектировании файловой системы COW.
Задача
Designing a copy‑on‑write filesystem from scratch with an AI agent requires a clear blueprint and a robust verification process to avoid hallucinations and biased conclusions.
Результат
The author achieved a clearer, more reliable design process for the COW filesystem, reducing reliance on a single AI and enabling focused human oversight.
Рабочий процесс
- Define design decisions (e.g., number of rooms, data format).
- Main Agent assigns Strong Agent to gather information and propose an answer.
- Supporter Agent searches for independent supporting evidence.
- Opponent Agent searches for strong counter‑evidence.
- Main Agent verifies validity of all reports and, if valid, repeats the process for a second round. If no result after three rounds, hand to human.
- Human reviews final summary and makes trade‑off decisions.
Доказательства
The implementer is an AI Agent. An Agent can write code toward a goal, but we lack a blueprint.
The conversation where the task starts is called the Main Agent. It only asks questions according to the plan.
Supporter B looks for non-overlapping supporting evidence for the answer, that is, other arguments that also support it.
Opponent C looks for arguments that show the answer does not hold at all. If he finds any, he reports them; otherwise he reports that he found none.
If, in this era, AI context has reached the million-token scale, the context window can even hold all the code and documentation of a medium-sized project at once.
- Дата записи: 2026-10-04T03:55:46.616Z