斯坦福如何教授 AI 原生工程：Mihail Eric 谈 CS146S 与 Monaco 实践
原标题：[One Million AI Engineer Special] How Stanford Teaches AI-Native Engineering — Mihail Eric, Monaco
AI 摘要
斯坦福讲师 Mihail Eric 在 CS146S 课程中引入开源维护者参与教学，要求学生熟悉陌生代码库、提出修改并向可能合并代码的维护者解释补丁。Mihail 同时负责 Monaco 的 AI 工作，他在访谈中介绍了课程大纲、编码智能体的循环与工具链、大型代码库的上下文工程，以及 Monaco 团队自建智能体工作区、购买代码审查工具并让值班智能体接入 Datadog 和 GitHub 的做法。他还讨论了代码审查瓶颈、安全与权限、后台智能体以及“买来学习、自建保留”的工具取舍原则。
正文节选
What do you assign when a coding agent can finish last year’s homework in one prompt? In the second run of Stanford’s CS146S, Mihail Eric brought open-source maintainers into the course. Students have to learn an unfamiliar repo, propose a change, and explain the patch to the person who might merge it. We invited Mihail, who teaches The Modern Software Developer at Stanford and leads AI at Monaco, to celebrate one million subscribers on the AI Engineer YouTube channel. He opens up the course syl