AI 导读
顺便说一句，这种架构也是编程的未来。 你可以把 Cursor Projects 理解为“面向编程的 Grok Bot”。思路是一样的，只是如果你想的话，能对子智能体、上下文等有更多可见性。 对我的音乐朋友们来说，这就像 GarageBand 对比 Logic Pro。
正文
This architecture is also the future of coding btw.
You can think about Cursor Projects like "Grok Bot for Coding". It's the same idea, just with more visibility into subagents, context, etc if you want.
It's like GarageBand vs. Logic Pro, for my music friends.
How do always-on, proactive agents like @Bot work? Watch my lecture at Stanford CS146S: 2:35 How we got here 6:13 What changed in the models 10:06 Inside an always-on agent 18:07 The harness 27:26 Context engineering 34:26 Where this is going在 X 查看被引用的帖子
来源：Lee Robinson · x.com