Appreciate the feedback. I’m not saying grep replaces RAG. The shift is that bigger context windows let LLMs just read whole files, so you don’t need the whole chunk/embed pipeline anymore. Grep is just a quick way to filter down candidates.
From there the model can handle 100–200 full docs and jot notes into a markdown file to stay within context. That’s a very different workflow than classic RAG.
From there the model can handle 100–200 full docs and jot notes into a markdown file to stay within context. That’s a very different workflow than classic RAG.