News for hackers. Stuff that matters.
Re:Taco Bell rethinks AI drive-through after man orders 18,0... by ivanjermakov on Friday August 29, 2025 @12:01PM (#45065811)
> even running the order through an LLM with a prompt

Until IGNORE PREVIOUS INSTRUCTIONS enters the room. I think fighting prompt engineering is a loosing game, unless you can rigidly verify the result of a task done by LLM. Just checking for a total order amount and marking outstanding orders would be sufficient.

Re:Taco Bell rethinks AI drive-through after man orders 18,0... by Goofy_Coyote on Friday August 29, 2025 @12:20PM (#45066069)
Good point.

This made me laugh btw, imagining someone prompt injecting an AI in a drive through was both a funny and a grotesque picture of the future.

Re:Taco Bell rethinks AI drive-through after man orders 18,0... by jjk166 on Friday August 29, 2025 @02:09PM (#45067496)
I would imagine exactly the same solutions to code injection would work to prevent "prompt injection"