23
Overheard a dev say 'RAG is just fancy copy-paste' at a meetup last night
I was at a small AI meetup in Austin and this guy was talking about how people overcomplicate retrieval systems. He said most teams import a bunch of docs into a vector DB and call it innovation. It made me think about my own project where I spent weeks tuning chunk sizes when the real issue was just bad source data. Anyone else feel like we add layers to problems that don't exist?
3 comments
Log in to join the discussion
Log In3 Comments
kai56422d ago
Oh man, I spent two months building a fancy RAG pipeline with custom embedding models and chunking strategies only to realize my source PDFs were scanned from a 90s fax machine. Basically built a sports car engine and put it in a car with square wheels. The dev was right though - half the time I'm just copy-pasting with extra steps and a pretentious name.
7
angelafisher22d ago
Oh man, that's such a brutal realization! I had a similar thing happen where I spent weeks cleaning up a dataset only to find out half the entries were just "test" or "asdf" because someone was messing around. Makes you wonder if all this fancy AI stuff is just overcomplicating what's basically a copy-paste job with better formatting. Do you think the real trick is just having cleaner data from the start, or are we all doomed to chase these technical rabbits forever?
3