智能体
x.com ·
@Addy Osmani (@addyosmani)
Addy Osmani：Agent 编码的质量来自可自运行的验证循环
Addy Osmani 认为，Agent 写代码“平均而言更好”的关键在于验证：测试、基准、规格和真实端到端运行等原本昂贵的检查，现在可以低成本交给 Agent 完成。因此工程重点不再是逐行审查，而是为 Agent 构建可自行运行的验证循环，并把每次错误固化为共享配置、hook 或测试，避免重复犯错。人类仍对发布负责，但审查对象从 diff 转向证据。
AI推荐理由 Addy Osmani 提出一个具体观点：Agent 写代码的规模化收益来自验证环节，测试、基准、规格和端到端运行等原本昂贵的检查现在可由 Agent 低成本执行，因此工程重心应从逐行审查转向构建 Agent 可自行运行的验证循环，并把错误沉淀为共享配置、hook 或测试。这是对 AI 编码工作流的可操作经验判断，对开发工具和 Agent 落地有参考价值；但属于个人观点帖，无数据或案例支撑，也未给出具体工具或实现细节，因此不能视为已验证结论。
72
浏览 38,396
点赞 527
评论 71
转发 44
正文
Agents write code "much better on average at scale" is right. The "at scale" part comes from verification. Agents make checking cheap.
The stuff that made "Good Code" expensive (tests, benchmarks, specs, real e2e runs) is now a cheap thing you can ask an agent for. You can improve the checks.
So our work is less "review every line" and more "build loops the agent can run itself". Give the agent a way to verify the work. That loop is where quality comes from.
And make taste compound. When the agent gets something wrong, write it down (shared config, a hook, a test) so it doesn't happen twice. A human still owns what ships but now they're reviewing evidence and not just diffs.