Re:I Built an AI Receptionist for a Luxury Mechanic Shop – P...
by rbtprograms on Monday March 23, 2026 @01:53PM
(#47492857)
in general these types of attacks are still difficult to solve, because there are a lot of different ways they can be formulated. llm based security is still and unknown, but mostly i have seen people using intermediary steps to parse question intent and return canned responses if the question seems outside the intended modality.
[ Parent
| on HN ]
There are no comments on this comment yet.