HackerNews中文版

一个表单同时完成了五项工作：判断状态、选择要打开的表单、获取数值、记录每个数值的来源，以及验证必填字段。自然语言保留了第三项功能，而将其他功能交给了模型。没有人记录下哪些功能被遗漏了。大型语言模型（LLMs）是通过填补空白进行训练的。现在我们已经从对话转向了行动，我们告诉它们不要填补空白。但没有人给它们提供一份不允许推断的内容清单，或者教它们如何在不推断的情况下填补空白。以下是对该清单和方法的尝试。https://github.com/Jang-woo-AnnaSoft/execution-state-preflight

查看原文

A form did five things at once: judged the condition, picked which form to open, took the values, carried where each value came from, and validated the required fields.Natural language kept the third one and gave the rest to the model. Nobody wrote down which ones went missing.LLMs were trained by filling in blanks. Now that we've moved from conversation to action, we tell them not to fill in blanks.But nobody has handed them a list of what they aren't allowed to infer, or shown them how to fill a blank without inferring.Here's an attempt at that list and that method.https://github.com/Jang-woo-AnnaSoft/execution-state-preflight/

表单完成了五件事。自然语言保留了一件。