This is based on a real app that someone is selling to real people. It's not a hit against AI, but it is very much a legitimate hit against uses of LLMs for this purpose.

Also, if LLMs worked as they are often advertised, they should have easily been able to answer "there isn't enough information in this picture to give you an accurate estimate. Try taking a picture of the label, or at least of the inside of the sandwich, or list the ingredients used".

▲

sjhatfield 17 hours ago | parent [-]

iAPS is not software you pay for. This is open source software to dose insulin where you assume full responsibility for the outcomes.

	▲	tsimionescu 16 hours ago \| parent [-]
		That's irrelevant to my point. Feel free to replace "selling" with "distributing" - my point stands: using an LLM to estimate carbs from a picture is a real use case that real software developers are suggesting to real people is a real solution. It's not some contrived idea that the researcher concocted to make AI look bad. The GP, and much of the thread, is basically acting as if it should be obvious to anyone who is not an idiot that this is not possible to do precisely; and that the researcher just made up some use case that LLMs can't do and wrote a paper about it to disparage AI.