Comment by zzril

Guardrails are essentially part of the input. Saying "but we have guardrails" is like saying "but we do trust part of the input".

Either way, even if you trust 100% of the input, there is actually no way to guarantee that you can trust the output of the LLM. (Which, I guess, is also true for every dependency you pull in. But for those, you at least have ways to audit them.)