与Agent协作并沉淀技能，才是最重要的智能体工作流
The most important agentic workflows are the ones where you collaborate with the…
The most important agentic workflows are the ones where you collaborate with the agent, verify its results, and encode them as a skill or verifier for reuse.
最重要的智能体工作流是那些你与智能体协作、验证其结果，并将其编码为技能或验证器以供复用的流程。
This works for things like writing, researching, coding, and other tasks.
这适用于写作、研究、编程等任务。
Domain expertise, in the form of human verification, is a crazy moat. Don't let anyone or any company tell you otherwise.
以人工验证形式存在的领域专长，是一道难以逾越的护城河。不要让任何人或任何公司告诉你并非如此。
And you can build incredibly valuable services and products with that. Protect it and don't give it away for free.
你可以借此构建极具价值的服务和产品。保护它，不要免费提供。
Keep upskilling yourself and leverage the AI agents along the way. But don't forget how crucial it is to develop and hone taste, judge quality, and critical thinking.
不断提升自己，并在此过程中善用AI智能体。但别忘了培养和磨练品味、评判质量以及批判性思维是多么关键。
In simpler terms, don't offload understanding to your AI systems. Offload all the rest (boring and repetitive tasks). Careful automation goes a very long way.
简而言之，不要将理解外包给你的AI系统。外包其余所有（枯燥且重复的任务）。谨慎的自动化能带来长远的好处。
A lot of the narrative today is around eliminating the need/replacing domain expertise. But if you work on hard problems, which you should be doing with AI, you realize quickly how primitive AI models are in their "intelligence", capabilities, and adapting to extremely hard and important domains. There is a reason why math problems continue to be solved only by folks with deep math backgrounds. Learn from that. I am not saying the models won't get better. They will get better, but so will humans (it's important to be an optimist in human intelligence for this to be crystal clear), and so the agent-to-human relationship and interactions are the real moat and where all the value and discovery will come from.
如今很多论调围绕消除对领域专长的需求或取代它。但如果你处理难题——这正是你应该用AI去做的事——你会很快意识到AI模型在“智能”、能力以及适应极其困难和重要领域方面的原始性。数学问题至今仍只有具备深厚数学背景的人才能解决，这是有原因的。从中学习。我并不是说模型不会变得更好。它们会变得更好，但人类也会进步（重要的是对人类智能保持乐观，才能看清这一点），因此智能体与人类之间的关系和互动才是真正的护城河，也是所有价值和发现的来源。
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力