Documentation is not trivial and AI-generated documentation sucks. As a technical writer, I find somewhat offensive this kind of pretentiousness from software developers. Documentation needs context, intentions, AND real-life use cases. And why the hell would you want to "synthesize documentation"? When you have great information architecture as well as supporting videos, there's no need to synthesize anything at all for the users."Clearly LLMs are useful to software engineers. They can quickly generate code, and they are excellent at synthesizing requirements and documentation. For some tasks this is enough: the requirements are clear enough, and the problems are simple enough, that they can one-shot the whole thing.That said, for anything non-trivial, they are not capable of maintaining enough context accurately enough to iterate to a working solution. You, the software engineer, are responsible for ensuring that the requirements are clear, and that the code actually does what it purports to do."zed.dev/blog/why-llms-cant-bui#AI #GenerativeAI #LLMs #Programming #SoftwareDevelopment #Chatbots #Documentation #SoftwareDocumentation
"I would never suggest that LLMs can be used to generate documentation beyond carefully delimited scenarios, such as API docs or code snippets, that is, cases where documentation is produced from clear and concise sources, in almost programmatic ways. Echoing the thoughts in Get the hell out of the LLM as soon as possible, you should limit LLM output to tasks where they truly excel.
On the other hand, when you let LLMs generate entire documentation sets, problems arise. “Oh, you can’t do serious programming, but you can still use LLMs for docs” is a naïve, reckless statement that not only overlooks what goes into crafting excellent documentation but also shows disregard for user experience (because docs are a product, too)."