Harrison Chase：概率输出比"让 LLM 决定"更容易上线
> feels way more shippable than "the LLM decided" probabilities are the underrated part of decis...
LangChain 创始人聊了个很实在的工程细节：让模型输出概率，设阈值、打日志、写测试，比直接说 LLM 决定的结果好上线多了。
LangChain 创始人 Harrison Chase 在 X 上发文，称概率是决策模型中被低估的部分。概率输出可以设置阈值、写入日志，并针对它们编写 eval 测试。他认为这种方式比只说"让 LLM 决定"更容易交付到生产环境。这条推文是与开发者 Hiếu Nguyễn Trung 的讨论串的一部分。
> feels way more shippable than "the LLM decided" probabilities are the underrated part of decis...
> feels way more shippable than "the LLM decided" probabilities are the underrated part of decision models you can threshold them, log them, write evals against them https://t.co/k4eRrMgNV0 Hiếu Nguyễn Trung @Hiumonday @hwchase17 honestly the probabilities are the best part. you can set a threshold, log it, write tests for it. feels way more shippable than "the LLM decided" 🔗 View Quoted Tweet 💬 0 🔄 0 ❤️ 0 👀 140 ⚡
