Hacker News new | ask | show | jobs
by 0123456789ABCDE 55 days ago
do you want to pollute the context with blurbs for docs in disparate topics? cascade filtering, even with naïve bm25, helps reduce the amount of _noise_ that's pushed into the context window. if we reduce the amount of results to consider, further filtering or reranking, with more expensive options, becomes realistic. one could even put a cheaper model in front to further clean the results.