[flagged]
Building Food Metadata with LLM Juries
11–16 of 16 posts
Re: Building Food Metadata with LLM Juries
#12Basically it’s AI on top of AI for metadata extraction. There are a lot of claims in the article but not a lot of hard data. In the end they still don’t know if the data is correct. Good luck with your glutes allergy. The weird thing for me is the prompt optimization loop? Why not fine tune the model instead of AI generating the prompt?
I am taking from their hero image that something like a gluten allergy would have to be verified by the merchant, but I’m just guessing that’s true.
Feeding failure cases into an AI-led prompt tuning agent to solve them seems prone to a lot of problems though.
Re: Building Food Metadata with LLM Juries
#13Basically it’s AI on top of AI for metadata extraction. There are a lot of claims in the article but not a lot of hard data. In the end they still don’t know if the data is correct. Good luck with your glutes allergy. The weird thing for me is the prompt optimization loop? Why not fine tune the model instead of AI generating the prompt?
Also, "healthy" as a boolean flag is, franky, a bit of a joke.
I'm guessing that if it is a real tag, then consumers have a "know it when I see it" feeling for certain kinds of food that they'd describe as "healthy." As a word that could be consistently well-defined, it's garbage. But that doesn't mean it's not useful for real-world consumers to find what they believe they want.
Re: Building Food Metadata with LLM Juries
#14Basically it’s AI on top of AI for metadata extraction. There are a lot of claims in the article but not a lot of hard data. In the end they still don’t know if the data is correct. Good luck with your glutes allergy. The weird thing for me is the prompt optimization loop? Why not fine tune the model instead of AI generating the prompt?
Also, "healthy" as a boolean flag is, franky, a bit of a joke.
If I search "healthy" in DoorDash, Taco Bell comes up in the top results
Re: Building Food Metadata with LLM Juries
#15despite having multibillion dollar valuation and a real product and service doordashes tech blogs have always been surprisingly simplistic and borderline elementary or in this case, kind of just slop. I remember reading their early data science ones and they were all sort of comically limited or discussing tradeoffs between outdated methods.
Re: Building Food Metadata with LLM Juries
#16[flagged]