Comment by sshine
6 days ago
Because support requires understanding. If you can maintain long-term context for the LLM, then you have an approximation of actionable institutional knowledge.
But context is text documentation, and that stuff rots just as much, if not more, when LLMs generate it.
Nothing beats having the actual code and the thoughts that went onto it in your wetware. I still remember the hardest problems in my professional life in the last 15 years down to a scary detail.
You can have the LLM generate whatever context you need- documentation, developers guide, design patterns, whatever. You can have it do this, at the time you create the app, or later (I have done this for other peoples code I found on GitHub that was commented in a language I can’t speak). You store this by having your LLM coding agent write it down in a file. I do that all the time. It works really well.
And if you have some kind of special case or something, the LLM will usually comment it when it writes it, but you can also just tell it to do so.
The docs don’t rot because you can throw them away and have the LLM recreate them at any time. And they’re not for you, they’re for the agent.
It’s a completely different mindset.