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

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

Boston Globe11-06-2025
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.
Get Winter Soup Club
A six-week series featuring soup recipes and cozy vibes, plus side dishes and toppings, to get us all through the winter.
Enter Email
Sign Up
'I want it to do as much as possible, short of actually preparing it,' Achatz said.
Advertisement
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.
Advertisement
'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.'
Goat sausage with butter beans and focaccia croutons at Houseman in Manhattan, May 29, 2025. Ned Baldwin, the restaurant's chef and owner, asked for ChatGPT's help in understanding the technical details of sausage-making.
EMON HASSAN/NYT
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.)
Advertisement
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 last month, 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.'
Visual renderings from AI helped chef Dave Beran talk to the architect and designer of his latest restaurant, Seline, in Santa Monica, Calif. 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?
Advertisement
'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 chefs may put a half-baked idea from ChatGPT on the menu, but plenty of chefs are already doing 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 story lines of a theatrical dining event somewhat in the mode of 'Sleep No More' that he will present this summer in Beverly Hills, Calif.
Advertisement
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.
ChatGPT, though, will stay up with him all night.
This article originally appeared in
.
Orange background

Try Our AI Features

Explore what Daily8 AI can do for you:

Comments

No comments yet...

Related Articles

Here's ChatGPT's advice on how to spot the next meme stock
Here's ChatGPT's advice on how to spot the next meme stock

Yahoo

timean hour ago

  • Yahoo

Here's ChatGPT's advice on how to spot the next meme stock

Amid this week's speculative euphoria, we asked ChatGPT what makes a meme stock. The chatbot laid out four things for investors to focus on. The AI also had some ideas about what stocks might be next in line for a short squeeze. What makes a meme stock? ChatGPT has a couple of ideas. When shares of Opendoor Technologies, a little-known online real estate platform, unexpectedly started surging this month, a few other seemingly random names followed. The list of stocks included Krispy Kreme, Kohl's, and GoPro, disparate companies united only by their financial challenges and vaguely retro vibes. On the surface, meme stocks that go parabolic have little in common, but if you look under the hood, there are some similarities in their profiles. How to find the next meme stock? We asked ChatGPT Since the GameStop short squeeze of 2021, investors have been trying to spot the next meme stock before it starts its ascent to the moon. After seeing some investors bragging on Wall Street Bets about getting winning trading advice from ChatGPT, we decided to test the AI's knowledge of the market's speculative frenzy. (We will preface all of this by saying it's not real investment advice. ChatGPT is scouring the internet—including Wall Street Bets! — for wisdom on the subject.) The prompt was: "What's the best way to identify what could be the next meme stock?" After clarifying what a meme stock is, the chatbot responded that identifying one is "more of an art than a science." It then proceeded to lay out some more detailed criteria for investors to think about: High short interest (>20% float), Days-to-cover ≥5The bot suggested Kohl's, Opendoor, and GoPro as examples of stocks with high interest from short sellers, naming and ShortInterestTracker as tools for assessment. Surge in social mentions (Reddit/Twitter)It highlighted the importance of noting sudden increases in a sock's mentions or upvotes on social media platforms such as X, Reddit and Discord, citing platforms including ApeWisdom and AltIndex. Unusual options activity (OI spikes)While discussing unusual options activity, it stated that "retail traders often pile into out-of-the-money (OTM) call options, creating gamma squeezes as market makers hedge by buying shares-fueling price surges." Meme narrative (pop‑culture, underdog story)ChatGPT highlighted the importance of a narrative, citing the David vs. Goliath mentality that drove the GameStop short squeeze or companies with products popular with retail investors, such as Krispy Kreme or AMC Entertainment, a fellow struggling meme stock. Wanting to test the AI's predictive abilities, we asked: "Based on this criteria, can you predict the next meme stock?" ChatGPT quickly named American Eagle Outfitters as its pick for the next meme stock based on its criteria, providing reasons it checks all four boxes. Per the bot: Social Media MomentumIts recent ad campaign starring Sydney Sweeney has ignited buzz across Reddit, X, and Stocktwits, pushing the stock up ~10% on the Interest & Squeeze PotentialWith ~13% of its float shorted, there's room for a squeeze if sentiment continues to climb. Options FlowEarly reports suggest call option volume has ticked upward around recent campaign news. Narrative + Meme-WorthinessThe Sydney Sweeney campaign taps into pop-culture, star power, and a viral storyline — all classic ingredients for meme stock fervor." Indeed, the fashion retailer's new ad campaign featuring Sweeney has made American Eagle a top trending stock across retail trading forums. While the stock is only up 11% for the week, the assessment shows that ChatGPT can spot trends as they're unfolding. Though it wasn't asked to, the chatbot added honorable mentions to what could be the next meme stock, including Krispy Kreme, GoPro, and Rocket Lab USA. It should be noted that these aren't great picks by the bot, as all of these stocks were already fading after surging earlier in the week. Meanwhile, RocketLab, though it has fairly high short interest, is not actually a meme stock. It is possible that ChatGPT confused it with Rocket Companies, which has much higher short interest and was among the meme shares to surge this the original article on Business Insider Sign in to access your portfolio

Meta just hired the co-creator of ChatGPT in an escalating AI talent war with OpenAI
Meta just hired the co-creator of ChatGPT in an escalating AI talent war with OpenAI

Business Insider

timean hour ago

  • Business Insider

Meta just hired the co-creator of ChatGPT in an escalating AI talent war with OpenAI

Shengjia Zhao, a co-creator of ChatGPT and former lead scientist at OpenAI, is joining Meta as chief scientist of its Superintelligence Labs. CEO Mark Zuckerberg announced Zhao's appointment on Friday in a social media post, and called him a "pioneer" in the field who has already driven several major AI breakthroughs. Zhao previously helped build GPT-4 and led synthetic data efforts at OpenAI. According to the post, Zhao will now work directly with Zuckerberg and Meta's newly appointed chief AI officer, Alexandr Wang, the founder and CEO of Scale AI. The new hire comes during Zuckerberg's multibillion-dollar AI spending spree, including a $15 billion investment in Scale AI and the creation of Meta Superintelligence Labs, a new division focused on foundational models and next-gen research. In addition to Zhao, the company has lured away the three researchers who built OpenAI's Zurich office — Lucas Beyer, Alexander Kolesnikov, and Xiaohua Zhai — all of whom previously also worked at Google's DeepMind. The Superintelligence Labs team is now comprised of a lineup of names previously seen with OpenAI, Anthropic, and Google. But the war for AI talent is far from over. Databricks VP Naveen Rao likened the competition to "looking for LeBron James," estimating that fewer than 1,000 people worldwide can build frontier AI models. Companies without the cash for massive pay packages are turning to hackathons and computing power as incentives. Perplexity CEO Aravind Srinivas said a Meta researcher he tried to poach told him to ask again when the company has "10,000 H100s." AI tech workers have previously told Business Insider that Meta's Mark Zuckerberg has been emailing prospects directly and even hosting AI researchers at his home, while OpenAI CEO Sam Altman has made personal calls to potential hires. Tech company executives have mixed feelings about Meta's poaching efforts. "Meta right now are not at the frontier, maybe they'll they'll manage to get back on there," said Demis Hassabis, the CEO of Google DeepMind, on an episode of the "Lex Fridman Podcast," which aired on Friday. "It's probably rational what they're doing from their perspective because they're behind and they need to do something," Hassabis added. During a July 18 episode of the podcast "Uncapped with Jack Altman," OpenAI CEO Sam Altman criticised some of Meta's "giant offers" to his company's employees, and called the strategy "crazy."

Meta just hired the co-creator of ChatGPT in an escalating AI talent war with OpenAI
Meta just hired the co-creator of ChatGPT in an escalating AI talent war with OpenAI

Business Insider

time2 hours ago

  • Business Insider

Meta just hired the co-creator of ChatGPT in an escalating AI talent war with OpenAI

Meta just escalated the AI talent war with OpenAI. Shengjia Zhao, a co-creator of ChatGPT and former lead scientist at OpenAI, is joining Meta as chief scientist of its Superintelligence Labs. CEO Mark Zuckerberg announced Zhao's appointment on Friday in a social media post, and called him a "pioneer" in the field who has already driven several major AI breakthroughs. Zhao previously helped build GPT-4 and led synthetic data efforts at OpenAI. According to the post, Zhao will now work directly with Zuckerberg and Meta's newly appointed chief AI officer, Alexandr Wang, the founder and CEO of Scale AI. The new hire comes during Zuckerberg's multibillion-dollar AI spending spree, including a $15 billion investment in Scale AI and the creation of Meta Superintelligence Labs, a new division focused on foundational models and next-gen research. In addition to Zhao, the company has lured away the three researchers who built OpenAI's Zurich office — Lucas Beyer, Alexander Kolesnikov, and Xiaohua Zhai — all of whom previously also worked at Google's DeepMind. The Superintelligence Labs team is now comprised of a lineup of names previously seen with OpenAI, Anthropic, and Google. But the war for AI talent is far from over. Databricks VP Naveen Rao likened the competition to "looking for LeBron James," estimating that fewer than 1,000 people worldwide can build frontier AI models. Companies without the cash for massive pay packages are turning to hackathons and computing power as incentives. Perplexity CEO Aravind Srinivas said a Meta researcher he tried to poach told him to ask again when the company has "10,000 H100s." AI tech workers have previously told Business Insider that Meta's Mark Zuckerberg has been emailing prospects directly and even hosting AI researchers at his home, while OpenAI CEO Sam Altman has made personal calls to potential hires. Tech company executives have mixed feelings about Meta's poaching efforts. "Meta right now are not at the frontier, maybe they'll they'll manage to get back on there," said Demis Hassabis, the CEO of Google DeepMind, on an episode of the "Lex Fridman Podcast," which aired on Friday. "It's probably rational what they're doing from their perspective because they're behind and they need to do something," Hassabis added. During a July 18 episode of the podcast "Uncapped with Jack Altman," OpenAI CEO Sam Altman criticised some of Meta's "giant offers" to his company's employees, and called the strategy "crazy." "The degree to which they're focusing on money and not the work and not the mission," said Sam Altman. "I don't think that's going to set up a great culture."

DOWNLOAD THE APP

Get Started Now: Download the App

Ready to dive into a world of global content with local flavor? Download Daily8 app today from your preferred app store and start exploring.
app-storeplay-store