Josef Chen releases EPICURE, a 2MB factor decomposition model mapping 1,790 ingredients from 4.1 million recipes
It identified five emergent culinary clusters without prior labels.
Me: Honey, I've got bad news and good news. Wife: ...what. Me: Bad news - I spent $1M of our savings on compute. Wife: AND THE GOOD NEWS?? Me: I found the vector between Chinese and Ethiopian cuisine Wife: Me: What? ethiopian - chinese is a surprisingly interpretable direction!!!
Launching our new paper on arXiv: we trained the largest multilingual food model ever built. 4.1M recipes. 7 languages. 1,790 ingredients. 300 dimensions. All of human cooking compressed into 2 megabytes.