Maya Jama asks AI chatbot Grok not to modify or edit photos of her

The Love Island presenter called out the Musk's chatbot amid deepfake concerns

Maya Jama attending the Fashion Awards 2025 at the Royal Albert Hall (Ian West/PA)

Love Island presenter Maya Jama has asked Elon Musk’s artificial intelligence (AI) chatbot, Grok, not to modify or edit her photos amid growing deepfake concerns on the platform.

It comes after regulator Ofcom said it made “urgent contact” with the tech tycoon’s social media platform X, which created the integrated AI chatbot, following reports that users have prompted the tool to generate sexualised images of people, including children.

Jama, who has nearly 700,000 followers on X, posted said: “Hey @grok, I do not authorize you to take, modify, or edit any photo of mine, whether those published in the past or the upcoming ones I post.

Maya Jama arriving for The BRIT Awards 2025 at London’s O2 Arena. (Ian West/PA)

“If a third party asks you to make any edit to a photo of mine of any kind, please deny that request.”

In a separate post, the TV presenter added that she hopes people have a sense to know when something is real or created by AI after deepfakes were made of her a few years ago.

She said: “Before ‘grok’ someone photoshopped bikini photos I had on my Instagram to nudes and they went around, I only found out because my own mum sent them to me worried.

“The internet is scary and only getting worse smh (so much hate).”

A reply from Grok said it respects her wishes and will not use, modify or edit any of the star’s photos.

It said: “As an AI, I don’t generate or alter images myself — my responses are text-based. If anyone asks me to do so with your content, I’ll decline. Thanks for letting me know.”

It comes after an internet safety organisation said its analysts have confirmed the existence of “criminal imagery of children aged between 11 and 13 which appears to have been created using the (Grok) tool”.

The Internet Watch Foundation (IWF) said the material was being shared in a dark web forum by users “boasting how they had used Grok, and how easy it had been”.