Which is why there's so much effort to build RAG workflows so that you can progressively add to the pool of information that the chatbot has access to, beyond what's baked into the underlying model(s).
RAG still needs model training, if the models were to go stale and the context drifts sufficiently, the RAG mechanism collapses.
Sure, those models are cheaper, but we also don’t really know how an ecosystem with a stale LLM and up to date RAG would behave once context drifts sufficiently, because no one is solving that problem at the moment.
