Reported by The Verge AI
I tested the new AI-powered tool on ingredient swaps, recipe scaling, and a missing Bundt pan.
Posts from this author will be added to your daily email digest and your homepage feed.
Around 7PM each weeknight, I find myself standing in front of the fridge, trying to decide on something for dinner that won’t make my husband complain, “Chicken again ?” Yes, I should meal plan more, but I don’t, so this is where I’m at. A nightly battle in which the chicken usually wins.
More from the original report
Recently, my best weapon in this fight has been AI. Between Alexa Plus in the Echo smart display on my kitchen counter, the Samsung Food app on my fridge, and even an AI-powered cooking robot , AI has become my go-to sous chef — albeit one I need to keep a close eye on. It’s helped me swap ingredients, generate ideas, fix things when I mess up, and yes, even cook better. So I was intrigued when my go-to recipe app, NYT Cooking, introduced an AI assistant .
Many, including some NYT Cooking users and recipe purists , are skeptical of this new tool (available to subscribers on iOS only at launch), and I get why. One of the things I like most about NYT Cooking is that it features thousands of recipes from dozens of reputable sources — such as the New York Times archives, restaurants, cookbooks, and food columnists — and real people have tested them. (I’ve tried some purely AI-generated recipes and they were not good).
Another great feature of the service, which I’ve been paying for for several years, is the reader comments. Here, I’ve often found solutions to cooking dilemmas, like what to substitute for makrut lime leaves — there’s always one slightly bougie ingredient in an NYT Cooking recipe that I don’t have on hand.
However, reading through hundreds of comments to find answers at 7PM on a weeknight isn’t always practical. And this is where I’ve found the NYT Cooking assistant helpful. Among other things, it was trained on user comments , and in my few days testing…