Advertisement
Advertisement
β‘ Community Insights
Discussion Sentiment
100% Positive
Analyzed from 226 words in the discussion.
Trending Topics
#documentation#great#more#docs#love#slides#projects#stale#taking#code
Discussion Sentiment
Analyzed from 226 words in the discussion.
Trending Topics
Discussion (5 Comments)Read Original on HackerNews
My LLM workflow is documentation-heavy, and that works great for getting projects off the ground and managing very large projects. But just like human-driven development, more documentation = more likelihood of being stale. Unlike humans, LLMs donβt resent time spent updating docs.
So, if youβre taking feature requests, I would love to see this head towards full lifecycle documentation management. The tricky part is figuring out whether the docs or code drifted. Sometimes misalignment means the code was built wrong, sometimes it means the docs are stale and changes are intentional. A HITL model should maybe help?
This invisible citation comment (<!-- slideops data-src="app/main.py:40-58"...) is added to Markdown documents to help with tracking changes and keeping them it sync with the codebase.
On the topic of generlaising to documents, for a moment I wish I named the skills "DocOps", but that's already a thing: https://www.writethedocs.org/guide/doc-ops/
It's somewhat inspired by literate programming, but a bit flipped.