[supermatt]

> no hallucinations possible

It can still hallucinate a response that is defined in the filter.

E.g if you have a filter with names of capital cities [“London”, “Paris”, “Madrid”] , and you ask “What is the capital of France” it could respond “Madrid”

[ycombinatrix]

Is that a hallucination, or is it just plain wrong?

[supermatt]

An AI hallucination is any response that contains false or misleading information presented as fact. So a wrong answer is an hallucination.