RAG Is Simpler Than You Think

Re:RAG Is Simpler Than You Think by woah on Wednesday August 26, 2026 @03:21PM (#49454405)

You do not know of prominent robust implementations? This is how Claude Code, GPT Codex, etc have worked for a couple years. And they do tend to be impressively good at navigating large amounts of text.

[ Parent | on HN ]

Re:RAG Is Simpler Than You Think by mdp2021 on Wednesday August 26, 2026 @05:12PM (#49455998)

Thank you, no, I did not know that. Where have you found the info? Sebastian Raschka, Anthropic/OpenAI blogs?

(BTW: you made me realize - I had to take "time off" for over half a year... I am sure I missed a lot.)

Edit: for clarity: for "full text search" we remain on the interpretation of "searching for literal substrings" - and whether plain user provided keywords list or LLM enriched list based on the former, and whether more or less successful, it remains a syntactic search quite distinct from a semantic one. Having an LLM enrich the original keywords list can be a good idea, but the possibility of misses remains when compared to a properly working semantic search.

[ Parent | on HN ]

Re:RAG Is Simpler Than You Think by antonvs on Wednesday August 26, 2026 @07:47PM (#49457481)

> Where have you found the info?

You can see it in action if you watch the “chain of thought” text when using coding agents.

[ Parent | on HN ]

Re:RAG Is Simpler Than You Think by woah on Wednesday August 26, 2026 @05:57PM (#49456474)

Yes, they navigate with heavy use of the "grep" tool

[ Parent | on HN ]