you are viewing a single comment's thread
view the rest of the comments
[–] 6 points 1 year ago (5 children)

LLMs, with a little coaxing, perform well at returning well formed JSON.

  • source
  • parent
  • hideshow 5 child comments
  • [–] 11 points 1 year ago (4 children)

    They do, my concern is more about if that JSON is correct, not just well-formed.

    Also, 18000 waters might be correct JSON, but makes an AI a bad cashier.

  • source
  • parent
  • hideshow 4 child comments
  • [–] 7 points 1 year ago* (3 children)

    There is a lot more that goes into it than just being correct. 18000 waters may have been the actual order, because somebody decided to screw with the machine. A human who isn't terminally autistic would reliably interpret that as a joke and would simply refuse to punch that in. The LLM will likely do what a human tells it to do, since it has no contextual awareness, it only has the system prompt and whatever interaction with the user it had so far.

  • source
  • parent
  • hideshow 3 child comments
  • [–] 1 point 1 year ago* (1 child)

    So they just trim the instructions so it doesn't take joke orders, so it can make more reasonable decisions, like:

    "May I take your order?"

    "Two double whoppers with extra mayo and a chocolate cherry banana sundae"

    "Oh you've GOTTA be joking!"

  • source
  • parent
  • hideshow 1 child comment