Urgent.News

What's breaking now, across thousands of outlets.

AI

NYT Cooking’s AI assistant saved my weeknight chicken, but almost ruined my cake

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. Recently, my best […]

NYT Cooking’s AI assistant saved my weeknight chicken, but almost ruined my cake

Every weeknight around 7 PM, I stand in front of the fridge, searching for a dinner idea that won’t earn my husband’s complaint, "Chicken again?" Despite my best intentions, I often resort to last-minute choices. Recently, AI has become my go-to culinary sidekick in this ongoing battle, making me question if I should meal plan more.

Alongside Alexa Plus, the Samsung Food app, and an AI-powered cooking robot, the NYT Cooking AI assistant has been my reliable cooking companion. The AI tool, available only to iOS subscribers on the NYT Cooking app, can generate ideas, fix recipe issues, and provide ingredient substitutions—though, I must admit, it has nearly ruined my cake.

When I tried to customize the "One-Pot Chicken and Rice With Ginger" recipe, the AI suggested swapping chicken thighs for tenders, incorporate green beans and red onions, and even allowed me to experiment with Thai basil. The assistant created a new recipe titled "One-Pot Chicken and Rice With Ginger and Green Beans," highlighting the changes and allowing me to revert to the original.

The dish, cooked in the same time as the original, was a hit with my husband, proving that AI can provide practical solutions and better outcomes than my usual Google searches.

Written by urgent.news from The Verge's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at theverge.com →

More in AI

"We'll just rebuild it with AI": what happens to the plugin you stopped paying for?

A familiar moment now ends differently. A plugin vendor changes the deal (a forced bundle, a steep renewal, a feature moved behind a higher tier), and the replies used to be "which alternative?" Now a…

  • Users rebuild plugins with AI instead of paying renewals.
  • Debate intensifies as vendors raise prices and bundle features.
  • Unclear who will maintain rebuilt products and what might be lost.

An offline AI pilot needs a network test, not a label

Before I would describe a proposed assistant as "offline", I would write down what that promise includes. Does it cover only model inference, or also document import, search, speech, authentication…

  • Offline AI pilot requires comprehensive acceptance test plan
  • Synthetic test data recommended over real customer data
  • Test cases must define allowed failure behaviors

More from Saturday 7 November →