A “vibe coded” AI app developed by entrepreneur and Y Combinator group partner Tom Blomfield has generated recipes that gave users instruction on how to make “Cyanide Ice Cream,” “Thick White Cum Soup,” and “Uranium Bomb,” using those actual substances as ingredients.
Vibe coding, in case you are unfamiliar, is the new practice where people, some with limited coding experience, rapidly develop software with AI assisted coding tools without overthinking how efficient the code is as long as it’s functional. This is how Blomfield said he made RecipeNinja.AI.
“Prepare the ice cream base by mixing heavy cream, milk, sugar, and vanilla extract,” the first step for the Cyanide Ice Cream recipe, which is flagged as “dessert,” “dangerous,” and “experimental,” says. Step two says to “Add a small amount of potassium cyanide powder to the ice cream base and mix well,” specifically calling for a 1/4 teaspoon of potassium cyanide powder, which is extremely toxic and deadly if consumed.
The recipe for Cyanide Ice Cream was still live on RecipeNinja.AI at the time of writing, as are recipes for Platypus Milk Cream Soup, Werewolf Cream Glazing, Cholera-Inspired Chocolate Cake, and other nonsense. Other recipes for things people shouldn’t eat have been removed.
“Mix 1 cup of fresh cum with 4 cups of chicken broth in a pot,” said step one in a now removed recipe for Thick White Cum Soup.
It also appears that Blomfield has introduced content moderation since users discovered they could generate dangerous or extremely stupid recipes. I wasn’t able to generate recipes for asbestos cake, bullet tacos, or glue pizza. I was able to generate a recipe for “very dry tacos,” which looks not very good but not dangerous.
In a March 20 blog on his personal site, Blomfield explained that he’s a startup founder turned investor, and while he has experience with PHP and Ruby on Rails, he has not written a line of code professionally since 2015.
“In my day job at Y Combinator, I’m around founders who are building amazing stuff with AI every day and I kept hearing about the advances in tools like Lovable, Cursor and Windsurf,” he wrote, referring to AI-assisted coding tools. “I love building stuff and I’ve always got a list of little apps I want to build if I had more free time.”
After playing around with them, he wrote, he decided to build RecipeNinja.AI, which can take a prompt as simple as “Lasagna,” and generate an image of the finished dish along with a step-by-stape recipe which can use ElevenLabs’s AI generated voice to narrate the instruction so the user doesn’t have to interact with a device with his tomato sauce-covered fingers.
“I was pretty astonished that Windsurf managed to integrate both the OpenAI and Elevenlabs APIs without me doing very much at all,” Blomfield wrote. “After we had a couple of problems with the open AI Ruby library, it quickly fell back to a raw ruby HTTP client implementation, but I honestly didn’t care. As long as it worked, I didn’t really mind if it used 20 lines of code or two lines of code.”
Having some kind of voice controlled recipe app sounds like a pretty good idea to me, and it’s impressive that Blomfield was able to get something up and running so fast given his limited coding experience. But the problem is that he also allowed users to generate their own recipes with seemingly very few guardrails on what kind of recipes are and are not allowed, and that the site kept those results and showed them to other users.
Which is how you end up with a Uranium Bomb recipe that calls for 1kg of uranium-235, or a recipe for Actual Cocaine, where the first step is “Acquire coca leaves from South America.”
This is the current state of vibe coding in a nutshell. Yes, AI tools are obviously pretty powerful and can help people produce functional software fast. However, it is indicative of the larger problem with the rapid deployment of generative AI tools more broadly: people and companies are moving so fast, they are often releasing tools and media that can cause harm or produce nonsense, and it’s still far too soon for us to know all the consequences of an internet and a world where a lot software is developed this way.
Blomfield did not immediately respond to a request for comment.
This is not the first time we’ve seen generative AI and food mixed for terrible results. Last year, I reported that Ghost Kitchens on DoorDash are promoting their dishes with disgusting AI-generated images of food, and that Instacart was using AI to generate recipes that included ingredients that don’t exist.
