Can you actually build a reliable customer-facing chatbot on top of LLM's? With the "jailbreaking" and not knowing if it's actually using the data you're supplying it or other data it was trained on and so on.

yes. there are a few approaches which i intend to take and some helpful resources:

You could implement a Dual LLM Pattern Model https://simonwillison.net/2023/Apr/25/dual-llm-pattern/

You could also leverage a concept like Kor which is a kind of pydantic for LLMs: https://github.com/eyurtsev/kor

in short and as mentioned in the README.md this is absolutely vulnerable to prompt injection. I think this is not a fully solved issue but some interesting community research has been done to help address these things in production

I'm not sure it solves the problem of restricting the information it uses though. For example, as a proof of concept for a customer, I tried providing information from a vector database as context, but GPT would still answer questions that were not provided in that context. It would base its answers on information that was already crawled from the customer website and in the model. That is concerning because the website might get updated but you can't update the model yourself (among other reasons).