LLM-docs
AI
llm documentation
SHOW HN2025
How HN took it
0 positive, 2 neutral or asking, 1 mixed, 0 critical, out of 3 comments about the project.
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Idea of machine-readable docs is valuable and fertile ground
From 1 comment
It’s a cool idea. I’ve wasted a lot of time over the past few months futzing around with beautifulsoup, Playwright and others I forget, or cloning entire repos and trying to…
darkteflon on HN
Objections
Distilled docs may not be what LLMs need; retrieval is the harder problem
From 2 comments
Yeah, agree that one could / should definitely put it through evals if it were going to be a product. There’s quite a bit to a good evals program, though. I think the main…
darkteflon on HNI feel like humans don’t have great intuitions around the ideal format for an LLM. But an LLM probably does have a good sense for what would work well for itself. And also I…
eigenvalue on HN
Token cost to generate docs is high and updates are costly
From 2 comments
- The maker's post
Why does it need to cost a lot of tokens, and why can't it incrementally update? How do the VS code integrated AI helpers do it?
eternityforest on HN
Requests
Plain text or markdown versions of docs rather than LLM summaries
From 1 comment
It’s a cool idea. I’ve wasted a lot of time over the past few months futzing around with beautifulsoup, Playwright and others I forget, or cloning entire repos and trying to…
darkteflon on HN
Evaluate distilled docs empirically with task-based evals
From 1 comment
I feel like humans don’t have great intuitions around the ideal format for an LLM. But an LLM probably does have a good sense for what would work well for itself. And also I…
eigenvalue on HN
Incremental updates instead of full regeneration
From 1 comment
Why does it need to cost a lot of tokens, and why can't it incrementally update? How do the VS code integrated AI helpers do it?
eternityforest on HN
Questions
Should the maker turn it into a full service?
From 1 comment
How do VS Code AI helpers index docs?
From 1 comment
Why does it need to cost a lot of tokens, and why can't it incrementally update? How do the VS code integrated AI helpers do it?
eternityforest on HN
Guidance on writing docs for LLM consumption
From 1 comment
Oh! Recently I had the experience of working with someone who was using LLMs to build something using my JS canvas library. The code the LLM was producing for this person was ...…
rikroots on HN
Alternatives named
Dagster's docs chatbot works well for RAG
From 1 comment
Dagster's docs must be LLM-readable somehow because their LLM that lets you ask questions about their docs is the best RAG experience I've had yet.
Noumenon72 on HN
Docling and unstructured for document conversion
From 1 comment
It’s a cool idea. I’ve wasted a lot of time over the past few months futzing around with beautifulsoup, Playwright and others I forget, or cloning entire repos and trying to…
darkteflon on HN