Thanks for pointing out the elephant in the room with LLMs.
The basic design is non-deterministic. Trying to extract "facts" or "truth" or "accuracy" is an exercise in futility.
My thesis isn't that we can stop the hallucinating (non-determinism), but that we can bound it.
If we wrap the generation in hard assertions (e.g., assert response.price > 0), we turn 'probability' into 'manageable software engineering.' The generation remains probabilistic, but the acceptance criteria becomes binary and deterministic.
Unfortunately, the use-case for AI is often where the acceptance criteria is not easily defined --- a matter of judgment. For example, "Does this patient have cancer?".
In cases where the criteria can be easily and clearly stipulated, AI often isn't really required.