Rolled out to iOS subscribers, the utility can execute specific adjustments such as advising cooks precisely when to substitute baby spinach for kale. All customized recipes generated through the system remain completely private and cannot be shared or published on the platform. Senior editor Genevieve Ko clarified that while the feature cannot be turned off, its use is entirely optional. New York Times spokesperson Jordan Cohen noted that many users are actively testing the capability with positive results.
Key points
The update builds upon previous platform automations, including imperial-to-metric conver…: The update builds upon previous platform automations, including imperial-to-metric conversions introduced two years ago and recipe scaling added last year.
Reader pushback centered on the environmental cost of artificial intelligence and concern…: Reader pushback centered on the environmental cost of artificial intelligence and concerns over altering the straightforward user experience.
The comment section closed after four days under standard moderation practices as represe…: The comment section closed after four days under standard moderation practices as representatives reported strong adoption from active users.
Sources checked by our analysis pipeline: 1
The New York Times is testing a new AI feature for its Cooking app that helps users to modify recipes, and it’s sparked some drama among users. NYT Cooking senior editor Genevieve Ko announced the feature last Friday, which can be used to recommend substitutions for ingredients and cooking equipment, scale recipes to any number of servings, and “generally make our recipes work for what a cook needs at that moment.”
The NYT Cooking app is testing AI recipe modifications
Some users aren’t exactly thrilled with the New York Times’ recipe tweaking AI tool.
Some users aren’t exactly thrilled with the New York Times’ recipe tweaking AI tool.
One of the examples given in the article shows a user asking to use baby spinach instead of kale, with the NYT Cooking app feature advising that because baby spinach wilts faster, it should be added during a later step of the recipe. Ko says it can also change the recipes around different pans and tools. Customized recipes are private and can’t be published or shared via the app. The AI modification…
The feature targets the limitations of single-turn testing by stress-testing AI systems across extended, sequential conversations where errors often compound. Operating within DigitalOcean Evaluations, it mirrors realistic engineering problem-solving to expose subtle operational failures. This framework provides teams with a systematic method to validate complex workflows before deploying agents into production environments.
Operating around the clock, an autonomous engineering agent built on the Nerve open-source runtime identifies root causes, compiles software, and resolves continuous integration failures. The system has expanded into fixing correctness and performance bugs across major database components, leaving human maintainers primarily to conduct code reviews. Its persistent memory architecture enables continuous learning from prior feedback to independently tackle intricate software investigations.
Arriving just over a week after the previous version, this patch showcases an agile framework that swaps specialized adapters on a single endpoint while keeping base models untouched. The system enables seamless component updates without migration friction or costly broader recomputation. These modular enhancements help enterprise developers roll out AI improvements with the velocity of traditional software releases.