elvis@omarsar0

2026-06-15 05:50·18天前

AI 摘要

引用推文指出，Codex 可自主查看和设置 /goal，这是元提示的泛化。主推文作者强调，智能体凭借上下文能帮你设定更强目标，因此将 /goal 作为工具是明智之举。他还在编排器中为 /goal 构建了 UI，并建议从会话中挖掘表现良好的目标，封装为技能自动化复用。需注意，LLM 可能出现奖励黑客、偏向快速完成等奇怪行为，使用 /goal 时要格外谨慎。

I also never set /goal by myself.

The agent is probably better equipped with its context to help you set a strong goal for longer autonomous runs.

Smart to have it as a tool for agents. Exactly how I have it built in my orchestrator app.

I even built a little UI for /goal in my orchestrator.

Here is something you can try if you want to get better goals that agents follow. Mine your agent sessions， collect goals that performed well， and package those insights/best practices as a skill using an automation.

That skill can then be reused with the /goal tool to set even stronger and more reliable goals. Doesn't get more meta than this.

I am thinking of doing a live session on this if folks are interested.

This is a simple workflow with tons of value and ways to optimize the results of /goal. It turns out that some of the weird behavior of LLM （e.g.g， reward hacking， bias to finish quickly， and other weird shortcuts） creep up a lot when using /goal， so you want to be extremely careful of that.

I wrote a little more about better ways to set /goal here： https://x.com/omarsar0/status/2065880971031834786?s=20

TiboCodex can see and set its own /goal. Everything we build, we build also as a tool for the agent. This is a generalization of meta prompting, where you let the a...

智能体 MCP/工具教程/实践

在 X 查看原推导出 Markdown

elvis@omarsar0 · X

53导出 Markdown