Should you let artificial intelligence plan your Thanksgiving dinner?

Maybe you’ve heard of poetry, comics, or award-winning art generated by artificial intelligence. How about an AI-generated Thanksgiving menu?

Thanksgiving is above all family recipes with a personal touch. Sure, tons of families eat turkey and stuffing on the fourth Thursday of November, but only a few can eat your grandma’s special stuffing or my dad’s meticulously slow-roasted turkey. So how could AI compete?

The New York Times decided to find out. The newspaper’s food team turned to GPT-3, a cutting-edge technology created by OpenAI that uses algorithms to generate text. Food journalist Priya Krishna started by providing the AI ​​tool with personal details about her background and eating habits.

“I am originally from Texas and grew up in a Native American family,” Krishna wrote. “I like spicy flavors, Italian and Thai cuisine and desserts that are not too sweet. Some ingredients I frequently cook with are chaat masala, miso, soy sauce, herbs, and tomato paste.

Then she asked GPT-3 for a Thanksgiving menu. She followed up with specific requests: “Show me some desserts tailored to my taste preferences. Show me a non-traditional Thanksgiving recipe. Show me a recipe for cranberry sauce that’s not too sweet and a little spicy.

The result was an ambitious Thanksgiving menu: pumpkin spice chaat, green beans with miso and sesame seeds, naan stuffing, roast turkey with a soy-ginger glaze, cranberry sauce “not too sweet and a little spicy” and pumpkin spice cake. with Orange Cream Cheese Frosting. GPT-3 generated recipes for each dish, and the Time The team also used DALL-E, OpenAI’s image generation tool, to create visuals for each element.

AI has already generated revenue. In 2016, Janelle Shane, a researcher who runs a blog called AI quirkiness, used AI tools to create recipes, then blogged about them. At the time, his findings were bizarre: They included recipes for ‘cream cheese soup’, ‘beef-style chicken stockings with salmon’ and ‘chocolate pickle sauce’, wrote BuzzFeedby Andy Golder in 2017.

The ingredients included meaningless items like ‘peeled rice’ and ‘chopped flour’, she tells the Time. But technology has come a long way in the past six years.

“What it does really well is make it sound plausible,” Shane says. “So if you weren’t paying attention and someone read this recipe out loud to you, you’d be, ‘Oh yeah, that sounds like a perfectly ordinary recipe.'”

Recipes in hand, Krishna and his colleagues got down to cooking and tasting. How were the dishes? In the lyrics of Time food columnist Melissa Clark: “We are not unemployed.

“The cake was dense and more salty than sweet,” writes Krishna. “The naan stuffing tasted like chana masala and fruitcake that had ended up in a bar. The roast turkey recipe called for a single clove of garlic to season a 12-pound bird, and no butter or oil; the result was dry and tasteless.

For those who want to put the AI ​​to the test in their own kitchen, the Time published the recipes online.

While AI isn’t replacing anyone’s grandmother’s recipes anytime soon, it still has food-related potential. For example, researchers at the University of Illinois published a study earlier this year exploring how machine learning models could help alleviate food insecurity. FortuneDanielle Bernabe, from , explains: “In some cases, AI and machine learning allow organizations to quickly collect and interpret large amounts of data to assess areas of need: predict where and why hunger is occurring. and ensuring effective food distribution.”