The space of palatable human food is small. There are only a few thousand ingredients and a few thousand preparation techniques. This could easily be compressed at high fidelity into a model.
The space of palatable human food is small. There are only a few thousand ingredients and a few thousand preparation techniques. This could easily be compressed at high fidelity into a model.
I say prove it. If it was a coding bot we would see some metrics on how it did. Have this thing produce a bunch of on demand recipes and judge it against human chefs. Have the people preparing the food cook according to its descriptions faithfully as either robots or non-cooking people so that their knowledge doesn't leak into the preparation. And then let's judge those recipes.
IF you need experienced culturally knowledgeable chefs to prepare the food for it to work, then you haven't encoded all the techniques, just crib notes.
Citations needed