I am sorry to be harsh but I find it a bit amateurish that they would use an AI generated hero image for this and presumably fabricated LLM output -- fabricated by an AI image generator no less

Whenever I create an image like this for the purpose of a demo, I make certain that it's either real input/output or at least exemplary of real input/output because that goes a long way towards instilling confidence in the tool. If the raw outputs aren't clean/comprehensible enough for presenting to stakeholders or others, fine, fabricate those or clean them up, but there's really no need to fabricate the image.

You might say "But they don't want to tie it to a particular restaurant or brand" -- you don't have to! Surely Doordash has generic food photos for this exact purpose

>Evaluators validate each tag individually — for example, protein, preparation, or health, individually rather than judging the item as a whole.

Am I reading this right that the jury is multiple LLMs each iterating through each tag and voting on each? Why wouldn't you tune one LLM to be really competent at a single tag? Like a single "spicy evaluator LLM" or "protein evaluator LLM"?

Basically 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?