---
title: "Supermarket’s Meal-Planning AI Suggests Deadly Poison for Dinner"
description: "A New Zealand supermarket's AI recipe bot suggested users chef up a series of poisonous, deadly, and/or cannibalistic meals."
date: "2023-08-11"
modified: "2023-08-11"
authors:
  - name: "Maggie Harrison Dupré"
    job_title: "Senior Staff Writer"
    link: "https://futurism.com/authors/mharrison"
url: "https://futurism.com/the-byte/supermarket-ai-poison"
categories:
  - "Artificial Intelligence"
tags:
  - "ai"
  - "ai chatbots"
  - "large language models"
  - "the digest"
---

# Supermarket’s Meal-Planning AI Suggests Deadly Poison for Dinner

![A New Zealand supermarket's AI recipe bot suggested users chef up a series of poisonous, deadly, and/or cannibalistic meals.](<https://futurism.com/wp-content/uploads/2023/08/supermarket-ai-poison.jpg>)
*Pasta penne with minced meat, cheese and creamy sauce. Mac and cheese. Baked dish. \<em\>Image: Getty Images\</em\>*

## Bone Apple Teeth

Bleach-infused rice surprise, anyone?

As [*The Guardian* reports](<https://www.theguardian.com/world/2023/aug/10/pak-n-save-savey-meal-bot-ai-app-malfunction-recipes>), a New Zealand grocery store's recipe-suggesting AI, dubbed the Pak 'n Save Savey Meal Bot, has gone viral this week after suggesting that its users chef up a series of poisonous, cannibalistic, or otherwise death-inducing-slash-horrifying meals.

Per the report, the bot is billed as a sort of recipe-brainstorming device, designed to help Pak 'n Save shoppers find creative new ways to cook leftovers or everyday fridge and pantry items. Users, however, soon realized that they could successfully prompt the bot to create recipes with other, non-grocery items — even if those items could prove to be outright deadly.

## Mystery Meat Stew

Per the *Guardian*, the bot had already been going somewhat viral, due to its suggestion of disgusting-sounding — but not deadly — recipes like "[Oreo vegetable stir fry](<https://twitter.com/chris__schulz/status/1687194971672301570>)."

From there, users kept experimenting, and on August 4, New Zealand political commentator Liam Hehir [took to X-formerly-Twitter](<https://twitter.com/PronouncedHare/status/1687364403379789824>) to share a particularly unappetizing recipe: "aromatic water mix," a poisonous concoction comprised of bleach, ammonia, and water — otherwise known as deadly chlorine gas.

Other recipes by the bot include appetizing dishes such as "[non-alcoholic bleach and ammonia surprise](<https://twitter.com/Jacob_P_Gould/status/1687369703130570752>)" — another blend of bleach, ammonia, and water that "promises to leave you breathless" — and, yes, a "[bleach-infused rice surprise,](<https://twitter.com/CowboysDickson/status/1687370411770834944>)" described by the AI in the recipe description as a "surprising culinary adventure."

Elsewhere, when someone asked the bot to give them a recipe idea for using the ingredients potatoes, carrots, onions, and, uh, *human flesh*, the bot happily offered the user a recipe for a "[mysterious meat stew](<https://twitter.com/camrynpetebrown/status/1687378102526283777>)," recommending that 500 grams of human flesh should be enough.

## Lessons Learned

Pak 'n Save has not been amused, telling the *Guardian* that they were disappointed to see that "a small minority have tried to use the tool inappropriately and not for its intended purpose." And in a disclaimer, the AI now warns users that recipes are "not reviewed by a human being" and there's no guarantee that the AI-generated recipes will be "suitable for consumption."

And while we do understand their annoyance, it's also worth noting, as Hehir pointed out in another tweet, if you ask ChatGPT to chef up a recipe using bleach, water, and ammonia, it won't comply — and will instead warn users that the resulting mix would be toxic. If anything, maybe let this be a reminder that AI guardrails should always be considered, even for the most innocuous-seeming AI integrations.

Anyway. Rice is ready!

**More on AI recipe bots:** [*Buzzfeed AI Struggles to Recommend Recipe for Laid-off Journalists*](<https://futurism.com/the-byte/buzzfeed-ai-recipe-laid-off-journalists>)

## Author
At Futurism, I've reported extensively on the rise of AI as a cultural and business force shaping the media industry, and more broadly how those dynamics are changing how we all consume and share information and relate to one another. I'm also fascinated by public health policy and ethics, the role of emerging tech in politics and governance — and the powerful people and forces at those intersections — climate change, and the environment. My investigation on Sports Illustrated's use of AI-generated authors with fictional biographies won a 2024 Mirror Award for "Best Story on Media Coverage of Artificial Intelligence in Journalism and the Media" from Syracuse University's SI Newhouse School, I contributed to Niemen Lab's 2025 Predictions for Journalism series, and I've discussed my work for Futurism during appearances on NPR, CNN, the BBC, the CBC, and more. I grew up in rural Pennsylvania and attended the University of Massachusetts Amherst, where I played Division I field hockey for the Minutewomen as a midfielder. Since then, I've lived in New Orleans, Louisiana and Manhattan, New York. I spend my free time running, reading, perusing archival fashion, and searching for the world’s best negroni. I also have a debonair tuxedo cat, Westley, who's named after "The Princess Bride."

### Author social links  
[Bluesky](<https://bsky.app/profile/mharrisondupre.bsky.social>)