I agree that LLMs are almost more likely than not to answer documentation questions wrong, to hallucinate methods that don’t exist, or just be silly. But the value I see in allowing LLMs to train on documentation is in the <i>glue code</i> that an LLM could (potentially!) generate.<p>Documentation, even good docs, usually only answer the question “What does this method/class/general idea do?” Really good docs will come with some examples of connecting A and B. But they will often <i>not</i> include examples of connecting A to E when you have to transform via P because of business requirements, and almost never tell you how to incorporate third-party libraries X, Y, and Z.<p>As an engineer, I can read the docs and figure out the bits, but having an LLM suggest some of the intermediary or glue steps, even if wrong sometimes, is a benefit I don’t get only from good documentation.