News for hackers. Stuff that matters.

A comment on What I learned building an AI coding agent for a year. Parent comment

Re:What I learned building an AI coding agent for a year by esafak on Saturday July 05, 2025 @10:06AM (#44472899)
The most robust way is not to index. Then you can't go wrong, but it is slower. People seem to be ok with it since the ML part takes longer -- for typical codebases, at least.

https://news.ycombinator.com/item?id=44106944

[ Parent | on HN ]
Re:What I learned building an AI coding agent for a year by jsnell on Saturday July 05, 2025 @10:22AM (#44473000)
I don't see how indexing is related to this? The question is about how to get the LLM to reliably apply the edit it wants to make. Even when the full current version of the file is in the context, this is one of the flakiest bits of the current LLM workflows.
[ Parent | on HN ]
Re:What I learned building an AI coding agent for a year by esafak on Saturday July 05, 2025 @10:25AM (#44473023)
In my mind the concern was about the LLMs mental model of what the files look like, which affects edits. I see where you're coming from too.
[ Parent | on HN ]