两个 Agent 互相审代码
Adversarial review between Codex and Claude
要点
- 在 Codex 里直接说 “Review this with claude”，在 Claude 里则说 “Review this with codex”。
- 模型自己会通过 CLI 发起审查、轮流发言，并把分歧争出结论。
- 不需要额外的技巧或配置，现成能力就够用。
原帖开头
Here's my technique for adversarial code review if I'm driving from Codex: "Review this with claude". And when I'm in Claude: "Review this with codex". Models know how to to kick off a review using the cli. Know how to take turns. Know how to settle an argument. No magic. …
