AI in the Kitchen: Renowned Chefs Explore ChatGPT for Recipe Creation

Famous Chef Boasts That He's Using AI to Invent New Recipes

Ethos seemed like one of Austin's hottest restaurants back in 2024. The eatery rose to prominence in October as tens of thousands of followers flocked to its Instagram page, a showcase of lustrous dishes such as the crustless pizza ball and the eye-grabbing dust mite bread loaf. There was only one small problem: Ethos only existed on Instagram, and its seemingly impossible bites were really just AI slop. Though the intentions behind the bizarre social media stunt remain a mystery, Ethos was a huge red flag, cautioning us on the slow creep of AI into the food and beverage industry. If it was intended as a warning, it was a prescient one. Over the months following Ethos' viral blowup, many in the restaurant industry have turned to large language model (LLM) software to roll out surge pricing, robo-marketing, employee surveillance, and kitchen automation to their eateries -- all in the name of saving a buck. Consider the award-winning chef Grant Achatz, who's turning to AI to do the creative task most cooks only dream of: creating the recipes for his restaurant menu. According to a new piece of tech stenography in the New York Times, Achatz -- several-time winner of the food industry's prestigious James Beard award -- is now using ChatGPT to churn out recipes for a nine-course meal at his Michelin-starred Chicago restaurant, Next. The restaurateur tasked ChatGPT with taking on the role of a different imagined chef for each course, each of whom draws from an emaciated slurry of real life culinary masters to provide inspiration for their "dish." For example, the NYT lists Jill, a "33-year-old woman from Wisconsin" who "trained" under the likes of Ferran Adrià, Jiro Ono, and Auguste Escoffier, as one of the AI creations. Achatz then instructed the chatbot to spit up recipes that "would reflect her personal and professional influences," which is a cutesy way to say "bastardize the work of some of the best craftsmen who've ever lived for a stunt." Case in point, Achatz told the newspaper that "I want it to do as much as possible, short of actually preparing it." While the celebrity chef and his cheerleaders at the New York Times -- the piece, notably, carries the byline of the paper's former restaurant critic Pete Wells -- may be impressed with themselves, many on social media find the idea revolting. "What an insult to Ferran Adrià, Jiro Ono, and the many talented chefs who work for Achatz that have actual experience that could be reflected in a dish," wrote one poster on Bluesky. "They should really headline it 'Grant Achatz is out of the ideas that make people pay $1,000 for dinner, is outsourcing his work to AI,'" quipped Sarah Orsborn, a veteran pastry chef based out of Denver. Achatz may have the final word on what leaves his kitchen, but the decision reads as particularly tasteless while many creatives and craftsworkers struggle against the widespread embrace of AI for creative labor. As recent as September 2024, for example, NPR reported that AI was generating recipes that could kill you if ingested -- even as tech companies ripped off the work of real life cooks to train their chatbots. In the present day, ChatGPT is still generating recipes like "burnt lettuce soup," which involves "boiling lettuce for 30 minutes before broiling it at 500 degrees," observed food critic Morgan Wujkowski. AI "lacks common sense and culinary experience," she wrote. "It follows algorithms, not tastebuds. Often times, the results that are generated are at best, incomplete, and at worst, faulty data." "Human creativity and intuition are paramount in recipe development, and it's the one major flaws in using AI to generate recipes," Wujkowski continued. "AI can assist in meal planning and macros, but actual human taste testing is irreplaceable. "

This year's hot new tool for chefs? ChatGPT.

For four months in 2026, the Chicago restaurant Next will serve a nine-course menu with each course contributed by a different chef. One of them is a 33-year-old woman from Wisconsin who cooked under the pathbreaking modernist Ferran Adrià, the purist sushi master Jiro Ono and the great codifier and systematizer of French haute cuisine, Auguste Escoffier. Her glittering resume is all the more impressive when you recall that Escoffier has been dead since 1935. Where did Grant Achatz, the chef and an owner of Next, find this prodigy? In conversations with ChatGPT, Achatz supplied the chatbot with this chef's name, Jill, along with her work history and family background, all of which he invented. Then he asked it to suggest dishes that would reflect her personal and professional influences. If all goes according to plan, he will keep prompting the program to refine one of Jill's recipes, along with those of eight other imaginary chefs, for a menu almost entirely composed by artificial intelligence. "I want it to do as much as possible, short of actually preparing it," Achatz said. As generative AI has grown more powerful and fluent over the past decade, many restaurants have adopted it for tracking inventory, scheduling shifts and other operational tasks. Chefs have not been anywhere near as quick to ask the bots' help in dreaming up fresh ideas, even as visual artists, musicians, writers and other creative types have been busily collaborating with the technology. That is slowly changing, though. Few have plunged headfirst into the pool in quite the way Achatz is doing with his menu for Next, but some of his peers are also dipping exploratory toes into the water, asking generative AI to suggest spices, come up with images showing how a redesigned space or new dish might look, or give them crash courses on the finer points of fermentation. "I'm still learning how to maximize it," said Aaron Tekulve, who finds the technology helpful for keeping track of the brief seasonal windows of the foraged plants and wild seafood from the Pacific Northwest that he cooks with at Surrell, his restaurant in Seattle. "There's one chef I know who uses it quite a bit, but for the most part I think my colleagues don't really use it as much as they should." The pinball-arcade pace of a popular restaurant can make it hard for chefs to break with old habits. Others have objections that are philosophical or aesthetic. "Cooking remains, at its core, a human experience," chef Dominique Crenn wrote in an email. "It's not something I believe can or should be replicated by a machine." Crenn said she has no intention of inviting a computer to help her with the menus at Atelier Crenn in San Francisco. It is true that generative AI consumes vast amounts of electricity and water. Then there are the mistakes. According to OpenAI, the company that owns ChatGPT, 500 million people a week use the program. But it is still wildly prone to delivering factual errors in a cheerily confident tone. (The New York Times has sued OpenAI and Microsoft, the creators of ChatGPT and other AI programs, alleging they violated copyright law by training their chatbots with millions of Times articles. The two companies have denied that.) None of the chefs I interviewed takes the chatbot's information at face value, and none will blindly follow any recipe it suggests. Then again, they don't trust most of the recipes they find in cookbooks or online, either. Cooks, like other humans, are forgetful, distracted and hemmed in by their own experiences. AI has its shortcomings, but these aren't among them. Chefs who consult the big electronic brain when they're devising a new dish or dining room find it helpful for the same reason bands like working with producer Brian Eno: Some of its suggestions are so unexpected that it can jolt them out of a creative rut. "You can get really hyper-specific ideas that are out of the box," said Jenner Tomaska, a chef in Chicago. For the Alston, a steakhouse he opened Friday, Tomaska wanted a variation on the Monégasque fried pastry known as barbajuan. ChatGPT's earliest suggestions were a little basic, but as he fed it more demanding prompts -- for instance, a filling that would reflect Alain Ducasse's style, steakhouse traditions and local produce -- the fillings got more interesting. How about Midwestern crayfish, white miso and fresh dill, with pickled celery root on the side? "It's a little bizarre, because I like to talk through these things with people, and I'm doing it with something that doesn't exist, per se," Tomaska said. But arming himself with ideas from his solitary talks with ChatGPT, he said, "does help bring better conversation to the creative process when I do have someone in front of me." Unlike most of one's friends and colleagues, generative AI has infinite patience for arcane and geeky topics. Ned Baldwin, the chef and owner of Houseman in Manhattan, began hounding ChatGPT with increasingly technical questions about the ins and outs of sausage-making after the first batch he made was too soft. It advised him about the relative binding merits of potato starch, tapioca flour and transglutaminase. It helped him understand the emulsifying properties of the protein myosin. And it went into the weeds on the chemistry that explains why overmixed sausage can become dry, grainy or rubbery. This is knowledge that many expert sausage makers "hold close to the chest," Baldwin said, and that some chefs may not want to admit they don't understand. "I think there's a certain point in your cheffiness where you're reluctant to be vulnerable and not know something," he said. But even if your prompts suggest you have the kitchen expertise of a toddler, he said, "ChatGPT will happily answer your question and not judge you." Not every kitchen idea starts with words. Tomaska was working on combining poblanos with spot prawns and tamarind for his restaurant Esmé when his sous-chef said it might be cool to serve it inside a ceramic poblano. They played around with Midjourney, an AI program that turns text into images. The pictures they got back looked glossy, a little garish and, like a lot of AI art, totally unreal. They sent them to a ceramist in Mexico City who designed a white poblano-shaped bowl that acts as a quiet foil for the coral-colored prawn. Another item on Esmé's menu began with Tomaska's giving a list of ingredients (Dover sole, cucumber, squash) to artist Paul Octavious, who plugged them into Midjourney. The resulting image was reworked as a kind of place mat for the final dish, which sits on top of it in a glass bowl and appears to be a response to it, as in fact it is. Visual renderings from AI helped chef Dave Beran talk to the architect and designer of his latest restaurant, Seline, in Santa Monica, California. He wanted a vibe that drew something from the shadowy, dramatic interiors of Aska in Brooklyn and Frantzén in Stockholm, but held more warmth. He kept prompting Midjourney to get closer to the feeling he wanted, asking it, for example, what if we had a fireplace that I wanted to curl up beside? "That was the mood we were trying to capture," Beran said. "Not dark and moody, but magical and mysterious." Midjourney's images looked like fantasy artwork, he thought. But the program acted as what he called "a translator" between him and his designer, giving them a common language. At the moment, AI can't build a restaurant or cook a piece of Dover sole. Humans have to interpret and carry out its suggestions, which makes the dining rooms and dishes inspired by AI in restaurants less unsettling than AI-generated art, which can go straight from the printer to a gallery wall. True, some chef may put a half-baked idea from ChatGPT on the menu, but plenty of chefs are already do this with their own half-baked ideas. For now, AI in restaurants is still inspiration rather than the final product. Since Achatz's first serious experiments with ChatGPT, about a year ago, it has become his favorite kitchen tool, something he used to say about Google. Its answers to his questions about paleontology and Argentine cuisine helped him create a dish inspired by Patagonian fossils at his flagship restaurant, Alinea. Before opening his latest restaurant, Fire, in November, he consulted ChatGPT to learn about cooking fuels from around the world, including avocado pits and banana peels. It has given him countless ideas for the sets, costumes and storylines of a theatrical dining event somewhat in the mode of "Sleep No More" that he will present this summer in Beverly Hills, California. Asked to evaluate how well Jill had integrated her training from Escoffier and Adrià in the dishes she proposed for Next, Achatz responded in an email. "Jill knows or researched important chefs and their styles, which very few chefs under 40 process today," he wrote. "She is young, and while experienced, does not yet have the understanding of how to blend them seamlessly." Years ago, he had similar blue-sky conversations at the end of the night with the talented cooks who worked with him at Alinea and Next, including Beran. He finds that batting ideas back and forth is "not of interest" for some of his current sous-chefs. "That dialogue is something that simply does not exist anymore and is the lifeblood of progress," he said.