The use of RAG (Retrieval Augmented Generation) is just another (freakin'!) WORKAROUND

I find it hard to buy the claims on the supposed hallucination improvements for LLMs by RAG (Retrieval Augmented Generation).

Seems to me that when RAG is claimed to work, it is because the external vector DB is giving almost the right answer to the prompt and LLM winds up… https://t.co/n4kHj0NIs9

— Subbarao Kambhampati (కంభంపాటి సుబ్బారావు) (@rao2z) November 11, 2023