> Switched to just letting the agent browse the directory tree and read files on demand -- it figured out the module structure in about 30 seconds

You guess what's the difference between code and loosely structured text...

There a lot of methods in IR/RAG that maintain structure as metadata used in a hybrid fusion to augment search. Graph databases is an extreme form but some RAG pipelines pull out and embed the metadata with the chunk together. In the specific case of code, other layered approaches like ColGrep (late interaction) show promise.... the point is most search most of the time will benefit from a combination approach not a silver bullet

Just like the approach in the article.

Everything is based on the metadata stored with chunks, just allowing the agent to navigate that metadata through ls, cd, find and grep.

This is an AI comment.

Parent may or may not be AI generated or AI edited. As such it MAY breach one of the HN commenting guidelines

Your comment however definitely breaches several of them.

Understood. I’m willing to defy guidelines and take the consequences. I still think it’s worth pointing out slop so people don’t waste their time talking to a machine.

indeed. moltbook vibes

I'd rather read a hundred comments like that than one more like yours.

Each to their own. I appreciate you writing that comment yourself.

I built tilth (https://github.com/jahala/tilth) much for this reason. Couldn't bother with RAG, but the agents kept using too many tokens - and too many turns - for finding what it needed. So I combined ripgrep and tree-sitter and some fiddly bits, and now agents find things faster and with ~40% less token use (benchmarked).