Original post · AI translation
OpenAI 构建了一个系统:有关 ChatGPT 运行变慢的警报会自动启动 Codex 智能体,后者查看日志和近期代码变更,以找出原因。
随后,第 2 个智能体尝试推翻这一诊断,另一个智能体则提出代码修复方案,交由人类工程师批准。
该系统善于查找原因,每天约进行 17 次调查,其中 70% 被认为准确,但修复是薄弱环节:在已诊断的 600 多个问题中,只有约 15 个由智能体自行提出的修复方案未经修改就得到上线。
Original
OpenAI built a system where alerts about ChatGPT slowing down automatically start Codex agents, which dig through logs and recent code changes to find the cause. A second agent then tries to prove that diagnosis wrong, and another proposes a code fix that a human engineer approves. It finds causes well, about 17 investigations a day with 70% judged accurate, but fixing is the weak part: out of 600-plus diagnosed problems, only about 15 of the agents’ own fixes shipped unchanged.