[DrSiemer]

My local LLM's are usually instructed to minimize hallucinations. My ChatGPT account has a custom prompt to this effect as well.

It literally says "If you do not know something, just tell me, don't make something up".

Also, "Don't worry about me feeling insulted, no need to apologize for everything", which eliminates a lot of the groveling.

When dealing with niche topics it helps to literally copy-paste relevant chunks of the manual in. You can't expect it to know about everything (yet).