Codex 的 /goal 命令解决了长任务执行痛点，做复杂自动化的开发者可以直接试。
OpenAI 的 Derrick Choi 团队撰文介绍了 Codex 中 /goal 命令的使用方法。该命令能让 Codex 持续工作直到目标被解决，而不是一次性地生成代码。文章详细说明了何时使用 Goals、激活 Goal 后会发生什么变化，以及如何编写具有清晰结果、约束条件和验证标准的 Goals。此外，还从架构层面解释了 Goals 的设计原理。这一功能对于需要长期、复杂任务自动化的开发者来说非常实用。
how to use /goal in codex — keep Codex working on a persistent objective until it's solved:
how to use /goal in codex — keep Codex working on a persistent objective until it's solved: Derrick Choi @derrickcchoi My colleagues wrote up a great post on using Goals in Codex. They go through when to use them, what changes when a Goal is active, and how to write Goals that give Codex a clear outcome, constraints and verification criteria. Also how we designed Goals at the architecture level if you’re curious. developers.openai.com/cookbook/examp… 🔗 View Quoted Tweet 💬 33 🔄 11 ❤️ 246 👀 23314 📊 57 ⚡