[xandre_maxwell]

Every now and then it's helpful! I hate how it tends to "guess" for me, though. And it's not hard questions, it's exactly the kind of boilerplate it's supposed to be good at. I'll ask things like how to connect to the Amazon API in Python for some quick boilerplate, or about a built in library in Python, and it'll just make stuff up. I often have to yell at it to not make stuff up 1 or 2 times before it gives me "real" code.

If I'm doing something obscure or niche forget it, it'll just make up a bunch of nonsense. But I wish it was easier to get it to say "I think it should work like x but I'm not sure about y part" instead of just going all in and making stuff up.

We need to train it on old LessWrong posts so it learns about degrees of belief and such lol

[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).