IBM’s artificial intelligence program Watson has been training to be a doctor over the last few years, applying its machine learning skills to genetics and cancer. But apparently the AI likes to cook in its spare time.
In a just-announced collaboration with Bon Appetit, Watson is using the 9000 or so recipes in the magazine’s database to generate new recipes based on available ingredients and a suggested cuisine style. The AI uses both the magazine’s archive and its own database of flavor compounds to determine what ingredients will go well together, and comes up with surprising new combinations. For more on how this works, check out the IEEE Spectrumarticle about IBM’s cooking initiative for Watson from last year’s special issue on food and technology
In Bon Appetit’s first test run with Watson, the AI simply suggested ingredients that could be used in dishes for a 4th of July menu, and the chefs were left to figure out how to combine berries and marjoram, for example, to make a cobbler. But IBM has since improved the program to include cooking instructions as well. The creators say they don’t expect cooks to necessarily follow Watson’s every directive, but they do believe the program can provide inspiration by suggesting unusual ingredients in unexpected combinations.
The collaborators have developed an app that will allow home cooks to have Watson in the kitchen with them, but it isn’t available for general release yet. You can apply to be a beta tester here.
Eliza Strickland is a senior editor at IEEE Spectrum, where she covers AI, biomedical engineering, and other topics. She holds a master’s degree in journalism from Columbia University.