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.

you are viewing a single comment's thread
view the rest of the comments
[–] 1 point 1 year ago (6 children)

Surely if the person making the order sees 18,000 waters they would think, hold on this doesn’t seem right maybe I should ask the customer if they really want 18,000 waters?

The same applies for the ice cream with bacon on it which was mentioned in the article. I believe a lot of these could be resolved with a bit of common sense.

  • source
  • parent
  • hideshow 6 child comments
  • [–] 8 points 1 year ago

    The same applies for the ice cream with bacon on it

    Does it, though? Unlike the 18,000 waters, if I were working a drive through I wouldn't even blink at an order for bacon ice cream. Heck, I might make a little extra to try it for myself!

  • source
  • parent
  • [–] 3 points 1 year ago (1 child)

    Sure, but how do you distill this into a rule a computer can follow? "Suspicious" is not an objectively measurable thing that a program can just check against

  • source
  • parent
  • hideshow 1 child comment
  • [–] -3 points 1 year ago

    Think the easiest way would be to collect order data for at least a good number of months if not a couple years and feed it in and use that as a baseline of what a typical human order looks like, anything that deviates too far from that baseline needs to be handled by a human until someone can validate it as a good order, though I imagine you could get false positives for new menu items unless you set a reasonable instruction for items that have never appeared in the dataset before.

  • source
  • parent