[jqpabc123]

https://www.ibm.com/think/topics/domain-specific-llm

[CamperBob2]

The article is not backed up by reality. Why would use anything but a domain-specific LLM, if they actually worked?

The author is probably confusing RAG with pretraining. You can RAG on PubMed but you can't arrive at a competitive model by pretraining solely on it.