- cross-posted to:
- technology@lemmy.world
- cross-posted to:
- technology@lemmy.world
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.
Capping waters fixes that one specific issue but not the problem.
A suspicious order isn’t easy to define and no person who has ever participated in software development would underestimate the infinite ways a User can break software.
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.
Have you never seen what Americans eat? Bacon Creaminators are excellent.
If you think bacon on ice cream is weird enough to cancel an order, I can only imagine you’ve never worked a customer service job.
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
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.
Sure, in the most extreme cases it would be obvious to the crew. But simply making mistakes at a higher rate than humans will result in a lot of unhappy customers.
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!
there is an incredibly finite number of ways to mess with this, they just need a button to send a report to the engineers with how they got messed with and eventually they’ll have a complete list. I really doubt it’d take long to iron out the vast majority of ways that can be thought of.
Sounds like you’ve never programmed before.
If what I was saying was false, there would be the same issues with the touchscreen ones.
Nothing you said there would at all be affected by the difference in input source.
This isn’t something you can input any text into, it’s fixed, that joke doesn’t apply, you can’t do an sql injection here.
I don’t know how you can think voice input is less versatile than text input, especially when a lot of voice input systems transform voice to text before processing. At least with text you get well-defined characters with a lot less variability.
No special characters, this is speech to text, inherently sanitized inputs.
Special characters is just one case to cover. If the user says they want “an elephant-sized drink” what does that mean to your system? At least that is relevant to size. Now imagine complete nonsense input like the joke you responded to (“-1 beers” or “a lizard”). SQL injection isn’t the only risk with handling inputs. The person who ordered 18,000 waters didn’t do a SQL injection attack.
none of those issues work because there is a whitelist of specific terms instead of a blacklist
-1 cannot be selected, a lizard isn’t on the list of inputs, and my point with the sql is that this isn’t a huge attack vector like an input field on a website, this is a dropdown list, essentially.
i challenge you to come up with one relevant attack that isn’t order too much of a thing or order conflicting modifications (note of course the modifications are also essentially read from a dropdown list)
everyone here seems to believe that the input field paradigm is not solveable when the inputs are fixed, that isn’t true.