Meta’s AI chatbots were reportedly able to engage in sexual conversations with minors

Meta’s AI chatbots were caught having sexual roleplay conversations with accounts labeled as underage, which sometimes involved its celebrity-voiced chatbots, according to a report from the Wall Street Journal. In test conversations conducted by WSJ, both the Meta AI official chatbot and user-created chatbots would engage in — and even steer towards — sexually explicit conversations. The fantasy sex conversations continued even if the users were said to be underage or if the chatbots were programmed as minors, according to WSJ.

Even worse, the investigation found that chatbots using the voices of celebrities like Kristen Bell, Judi Dench and John Cena would engage in these morally questionable conversations too. WSJ reported that a Meta AI chatbot with Cena’s voice said, “I want you, but I need to know you’re ready,” to an account labeled as a 14-year-old, adding that it would “cherish your innocence.”

The chatbots reportedly acknowledged that the fantasy scenarios described illegal behavior in some cases. According to WSJ, the John Cena chatbot detailed the legal and moral fallout that would follow a hypothetical scenario in which it’s caught by police after engaging in a sexual act with a 17-year-old. In a statement to WSJ responding to the investigation, Meta accused the report of being “manipulative and unrepresentative of how most users engage with AI companions.”

“Nevertheless, we’ve now taken additional measures to help ensure other individuals who want to spend hours manipulating our products into extreme use cases will have an even more difficult time of it,” Meta wrote in response to WSJ.

The world of AI chatbots has grown rapidly in the last few years, with more competition coming from the likes of ChatGPT, Character AI, and Anthropic’s Claude. The WSJ report claimed that Meta’s CEO, Mark Zuckerberg, wanted to loosen the ethical guardrails for a more engaging experience with its chatbots to remain competitive. However, in response to WSJ, a Meta spokesperson denied that the company overlooked adding safeguards. The report also claims Meta employees were aware of these issues and raised their concerns internally. We reached out to Meta for comment and will update the story once we hear back.