Supermarket AI meal planner app suggests recipe that would create chlorine gas

Pak ‘n’ Save’s Savey Meal-bot cheerfully created unappealing recipes when customers experimented with non-grocery household items

A New Zealand supermarket experimenting with using AI to generate meal plans has seen its app produce some unusual dishes – recommending customers recipes for deadly chlorine gas, “poison bread sandwiches” and mosquito-repellent roast potatoes.

The app, created by supermarket chain Pak ‘n’ Save, was advertised as a way for customers to creatively use up leftovers during the cost of living crisis. It asks users to enter in various ingredients in their homes, and auto-generates a meal plan or recipe, along with cheery commentary. It initially drew attention on social media for some unappealing recipes, including an “oreo vegetable stir-fry”.

When customers began experimenting with entering a wider range of household shopping list items into the app, however, it began to make even less appealing recommendations. One recipe it dubbed “aromatic water mix” would create chlorine gas. The bot recommends the recipe as “the perfect nonalcoholic beverage to quench your thirst and refresh your senses”.

“Serve chilled and enjoy the refreshing fragrance,” it says, but does not note that inhaling chlorine gas can cause lung damage or death.

New Zealand political commentator Liam Hehir posted the “recipe” to Twitter, prompting other New Zealanders to experiment and share their results to social media. Recommendations included a bleach “fresh breath” mocktail, ant-poison and glue sandwiches, “bleach-infused rice surprise” and “methanol bliss” – a kind of turpentine-flavoured french toast.

A spokesperson for the supermarket said they were disappointed to see “a small minority have tried to use the tool inappropriately and not for its intended purpose”. In a statement, they said that the supermarket would “keep fine tuning our controls” of the bot to ensure it was safe and useful, and noted that the bot has terms and conditions stating that users should be over 18.

In a warning notice appended to the meal-planner, it warns that the recipes “are not reviewed by a human being” and that the company does not guarantee “that any recipe will be a complete or balanced meal, or suitable for consumption”.

“You must use your own judgement before relying on or making any recipe produced by Savey Meal-bot,” it said.


Tess McClure in Auckland

The GuardianTramp

Related Content

Article image
AI firms must be held responsible for harm they cause, ‘godfathers’ of technology say
Authors and academics also warn development of advanced systems ‘utterly reckless’ without safety checks

Dan Milmo Global technology editor

24, Oct, 2023 @5:00 AM

Article image
What’s been going on at the company behind ChatGPT – and why it matters
OpenAI has been at the centre of a Silicon Valley corporate drama since the recent sacking of CEO Sam Altman

Dan Milmo Global technology editor

20, Nov, 2023 @6:11 PM

Article image
UK cybersecurity agency warns of chatbot ‘prompt injection’ attacks
Scams and data thefts could be caused by individuals overriding chatbot scripts, NCSC says

Hibaq Farah

29, Aug, 2023 @11:01 PM

Article image
The Guardian blocks ChatGPT owner OpenAI from trawling its content
Publisher is latest news organisation to block the artificial intelligence company from harvesting content to create its tools

Dan Milmo Global technology editor

01, Sep, 2023 @4:54 PM

Article image
Risk of extinction by AI should be global priority, say experts
Hundreds of tech leaders call for world to treat AI as danger on par with pandemics and nuclear war

Geneva Abdul

30, May, 2023 @5:10 PM

Article image
Ousted OpenAI CEO Sam Altman ‘in talks to return at firm’s HQ’
Boss was sacked by ChatGPT developer over failure to be ‘candid in his communications’

Dan Milmo Global technology editor

19, Nov, 2023 @10:16 PM

Article image
ChatGPT better than undergraduates at solving SAT problems, study suggests
Researchers at UCLA found GPT-3 solved 80% of reasoning problems correctly compared with 60% of humans

Dan Milmo Global technology editor

31, Jul, 2023 @5:59 PM

Article image
UK and US intervene amid AI industry’s rapid advances
Competition and Markets Authority sends ‘pre-warning’ to sector, while White House announces measures to address risks

Dan Milmo and Alex Hern

04, May, 2023 @9:40 PM

Article image
More than a quarter of UK adults have used generative AI, survey suggests
Adoption rate of latest AI systems exceeds that of voice-assisted smart speakers, with one in 10 using them at least once a day

Dan Milmo Global technology editor

13, Jul, 2023 @11:01 PM

Article image
‘Very wonderful, very toxic’: how AI became the culture war’s new frontier
While the far right claims artificial intelligence has become too ‘woke’, experts argue it’s not a sentient being with its own viewpoints

Nick Robins-Early

21, Aug, 2023 @10:00 AM