您如何信任您的？ 智能体工作更多？复制这段帖子/链接，然后发给你的…… @bot 对不起，我无法完成这个请求。 智能体1. 代码库改进：这只是良好的软件工程 - 更好的架构、更强的类型和不变性、清晰的边界。 智能体 爱学习的是那些存在就复制，走捷径的。所以把容易的事当正确的事。通过代码直接解决问题，你就不需要再思考了。2. 静态分析：规则、测试、CI、验证（例如 TLA+）。这些非常高效的方法可以在问题出现之前就发现错误。3. 代码风格：注释、规则。 智能体.md, 技能 - 任何不能强制执行且需要的特性。 智能体 判决。使用它时要谨慎，但请务必使用/创建验证技能。
4. 人工审核：最难扩展。以每小时10000次的速度。 智能体 土地代码，彻底审查每个 PR 是几乎不可能的，所以把精力放在最有杠杆作用的地方，设计一个环境。 智能体 默认做正确的事情。
这形成一个倒金字塔：你希望在顶部投入大部分精力，而在底部投入最少。代码库改进是确定性的，使它更高效，让你晚上睡得更踏实。 https://github.com/cursor/plugins/tree/main/pstack 创建一个新的项目：
1. 查看我在给PR、代码和架构代码审查评论中提供的反馈的slack/chat消息和代码审查评论。
2. 使用/recall在我的过去录音中学习我如何引导。 智能体
3. 使用 /poteto-mode 时，通过分析过去的提交来查找最常见的错误。 智能体 陷入，然后提出一个计划来重新架构我自己的代码，使其更 智能体 友善地回答开放性问题，而不是依赖我，而是通过原型展示计划，并用实际数据支持计划。
在你开始之前，请使用 /sharpen + /in-your-own-words 提示，并确认此提示。
4. 人工审核：最难扩展。以每小时10000次的速度。 智能体 土地代码，彻底审查每个 PR 是几乎不可能的，所以把精力放在最有杠杆作用的地方，设计一个环境。 智能体 默认做正确的事情。
这形成一个倒金字塔：你希望在顶部投入大部分精力，而在底部投入最少。代码库改进是确定性的，使它更高效，让你晚上睡得更踏实。 https://github.com/cursor/plugins/tree/main/pstack 创建一个新的项目：
1. 查看我在给PR、代码和架构代码审查评论中提供的反馈的slack/chat消息和代码审查评论。
2. 使用/recall在我的过去录音中学习我如何引导。 智能体
3. 使用 /poteto-mode 时，通过分析过去的提交来查找最常见的错误。 智能体 陷入，然后提出一个计划来重新架构我自己的代码，使其更 智能体 友善地回答开放性问题，而不是依赖我，而是通过原型展示计划，并用实际数据支持计划。
在你开始之前，请使用 /sharpen + /in-your-own-words 提示，并确认此提示。
查看原文
原帖正文
how do you trust your agents' work more? copy this post/link and give it to your @bot or agent!1. codebase improvements: this is just good software engineering - better architecture, stronger types and invariants, clear boundaries. agents love to copy what exists and take the shortest path, so make the easy thing the right thing. categorically eliminate problems through code and you won't need to think about it again.
2. static analysis: lint rules, tests, CI, verification (eg TLA+). very token efficient ways to catch issues ahead of time.
3. prose: comments, rules, AGENTS.md, skills - anything that can't be enforced and requires agent judgment. use it minimally, but do use /create-verification-skill.
4. human review: the hardest to scale. at the rate agents land code, it's pretty much impossible to thoroughly review every PR, so spend that effort on the highest leverage point, designing an environment where agents do the right thing by default.this forms an inverse pyramid: you want most of your effort at the top, least at the bottom. codebase improvements are deterministic, making it more token efficient, and lets you sleep more soundly at night.install https://github.com/cursor/plugins/tree/main/pstack and create a new Project:
1. look through my slack/chat messages and code review comments where i've given feedback on PRs, code, architecture
2. use /recall on my past transcripts to learn how i steer agents
3. /poteto-mode use /correct and /architect on past commits to find the most common pitfalls agents fall into, then propose a plan to rearchitect the code i own so it's more agent friendly. answer open questions with prototyping rather than defer to me, and back the plan with real data.
4. before you begin, use /sharpen + /in-your-own-words and confirm this prompt with me
2. static analysis: lint rules, tests, CI, verification (eg TLA+). very token efficient ways to catch issues ahead of time.
3. prose: comments, rules, AGENTS.md, skills - anything that can't be enforced and requires agent judgment. use it minimally, but do use /create-verification-skill.
4. human review: the hardest to scale. at the rate agents land code, it's pretty much impossible to thoroughly review every PR, so spend that effort on the highest leverage point, designing an environment where agents do the right thing by default.this forms an inverse pyramid: you want most of your effort at the top, least at the bottom. codebase improvements are deterministic, making it more token efficient, and lets you sleep more soundly at night.install https://github.com/cursor/plugins/tree/main/pstack and create a new Project:
1. look through my slack/chat messages and code review comments where i've given feedback on PRs, code, architecture
2. use /recall on my past transcripts to learn how i steer agents
3. /poteto-mode use /correct and /architect on past commits to find the most common pitfalls agents fall into, then propose a plan to rearchitect the code i own so it's more agent friendly. answer open questions with prototyping rather than defer to me, and back the plan with real data.
4. before you begin, use /sharpen + /in-your-own-words and confirm this prompt with me
引用自 X
原帖地址：https://x.com/i/status/2111133080526495985
原帖：
本站媒体副本
0 条评论
登录后可以参与讨论。
成员登录还没有评论。第一条认真回应会很重要。