If an LLM can't be trusted with a fast food order, I can't imagine what it is reliable enough for. I really was expecting this was the easy use case for the things.

It sounds like most orders still worked, so I guess we'll see if other chains come to the same conclusion.

Comments

cross-posted from: https://lemmy.sdf.org/post/41849856

If an LLM can't be trusted with a fast food order, I can't imagine what it is reliable enough for. I really was expecting this was the easy use case for the things.

It sounds like most orders still worked, so I guess we'll see if other chains come to the same conclusion.

This is just a hilarious misapplication of AI. Classic "what could possibly go wrong" idiocy. Were there only prior art ...

Last year McDonald's withdrew AI from its own drive-throughs as the tech misinterpreted customer orders - resulting in one person getting bacon added to their ice cream in error, and another having hundreds of dollars worth of chicken nuggets mistakenly added to their order.