学会构建 eval:用智能体加定时任务完成知识工作的实用建议
Garry Tan 分享了个很实在的玩法:让智能体写 markdown 技能再挂 cron 自动跑,加上学会做 eval 就能在自己领域里领先。
Garry Tan 提出一种工作方式:让智能体编写 markdown 格式的技能文件,再放到 cron 定时任务里运行,可以覆盖大多数知识工作场景。Elvis Saravia 补充强调,在智能体之上再构建一套好的 eval,是快速在特定领域或任务上达到前沿水平的关键。两人共同的观点是:eval 能力本身就是一种可复用的竞争优势。
Indeed. I would add that if you know how to build a good eval on top of it, you will be on the frontier in your domain/task in no time. That is the kind of edge that evals can unlock for you. Learn to build good evals too. It's worth it. Garry Tan @garrytan You can basically work with agents to write markdown skills and put it on a cron job and do almost every useful type of knowledge work now 🔗 View Quoted Tweet 💬 8 🔄 1 ❤️ 13 👀 2442 📊 8 ⚡