减轻 AI 改动带来的认知负担
Andrew · 2026年10月1日 · 2 分钟阅读
审阅 AI 生成的大量代码时,我常发现,大语言模型(LLM)给抽象概念挑的词,并不总能对上我自己会用的词。比如,它可能把某个东西叫作 MutationIntent,但在我看来,叫 EditRequest 更自然。因为 LLM 选词不是我的理想选择,每次看到它,我都得在脑子里查一遍它到底指什么,这就增加了认知负担。
这看起来只是个小摩擦,但在一段陌生代码里,当几十个新术语相互交织时,认知负担就会累积。我脑子里能同时记住的语义对照数量有限,一旦超出,就开始误解代码的运作方式。
为了尽量减轻这种情况,我会在审阅前用下面这段提示词对 AI 的改动做后处理:
Please review the changes and extract any unconventional or bespoke terms used for abstract objects, processes and concepts. Create a temporary markdown file with each term, its meaning and why it was chosen, and some proposed alternative terms for it. I will then use this markdown file to confirm the term choice or to provide my own custom term. You will then incorporate any changes. The goal here is to map your language choices to my own language choices so that I can understand the concepts more easily.