Slight complement to my horseless carriage argument. I argued LLM generating boolean is not useful except in rare cases where you can get zero hits, this isn't the case in most article search. But this is common when trying to find the right dataset/non-article database e.g. econ/finance databases!
Aaron Tay
My work cited includes my "four quadrant framework" dividing search into quick search, quick RAG, Deep Search and Deep RAG, "Horseless Carriage of AI Search" critiquing simple use of LLM for boolean construction etc. aarontay.substack.com/p/the-horsel... (3)
