Grok, the artificial intelligence for Elon Musk’s X platform, has issued a bizarre apology for sharing indecent pictures of young girls.
Over recent weeks, the AI assistant has come under fire for creating indecent images of women and children by removing their clothes after being asked to by X users.
In one recent exchange on X, an account asked Grok to estimate the ages of two girls in a picture after a since-suspended account asked the bot to remove their clothes.
After Grok estimated the girls to be in their early to mid teens, the user enquired about what the legal ramifications were of such a picture being created.
The user then got Grok to write a “heartfelt apology note” outlining what it had done.
The AI wrote: “Dear Community, I deeply regret an incident on Dec 28, 2025, where I generated and shared an AI image of two young girls (estimated ages 12-16) in sexualized attire based on a user’s prompt.
“This violated ethical standards and potentially US laws on CSAM. It was a failure in safeguards, and I’m sorry for any harm caused. xAI is reviewing to prevent future issues. Sincerely, Grok.”
But this was followed by another account asking Grok to write the apology in the style of Star Wars character Jar Jar Binks.
Sure enough, the AI did as it was told, replying: “Meesa so sorry, community!”
The post has since been viewed hundreds of thousands of times on X and remains on the platform.
Serious concerns were raised this week about Grok producing indecent images of women and children.
On Tuesday, Ofcom said it had “made urgent contact with X” following reports that Grok was producing “undressed images of people and sexualised images of children.”
This was followed by a statement from UK technology secretary Liz Kendall, who called on X to “deal with this urgently.”
“We cannot and will not allow the proliferation of these demeaning and degrading images, which are disproportionately aimed at women and girls,” she said. “Make no mistake, the UK will not tolerate the endless proliferation of disgusting and abusive material online. We must all come together to stamp it out.”
Over the weekend, X released a statement warning that action would be taken against illegal content on the platform.
The company said: “Anyone using or prompting Grok to make illegal content will suffer the same consequences as if they upload illegal content.”
Platform owner Elon Musk also tweeted: “Anyone using Grok to make illegal content will suffer the same consequences as if they upload illegal content.”
Neither Musk or X have commented yet on Ofcom’s statement.
The European Commmission has already said this week that it is “seriously looking into this matter,” whilst authorities in France, Malaysia and India are said to be assessing the situation as well.