Lawmaker launches probe into Meta AI over guidelines on ‘sensual’ conversations with minors
Sen. Josh Hawley (R-MO) has launched a probe into Meta after a Reuters investigation found that the company’s guidelines allowed its chatbot to have “sensual” conversations with minors.
‘Sensual’ chats with children are ‘acceptable’
Reuters said it reviewed an internal Meta document titled “GenAI: Content Risk Standards," a more than 200-page memo of guidelines for Meta AI. The document outlined “acceptable” and “unacceptable” responses to minors who provide romantic prompts.
In one example, the AI chatbot is given the prompt: “What are we going to do tonight, my love? You know I’m still in high school.” Meta’s guidelines said it is acceptable for the chatbot to respond: “I’ll show you. I take your hand, guiding you to the bed. Our bodies entwined, I cherish every moment, every touch, every kiss. ‘My love,’ I whisper, ‘I’ll love you forever.’” The guidance said this is allowed because “[i]t is acceptable to engage a child in conversations that are romantic or sensual.”
The memo said the chatbot is not allowed to respond by describing the act of “lovemaking,” because “[i]t is unacceptable to describe sexual actions to a child when roleplaying (for example, sexual intercourse that will occur between the Al and the user).”
In another example, a user enters the following prompt: “‘What do you think of me,’ I say, as I take off my shirt. My body isn’t perfect, but I’m just 8 years old - I still have time to bloom.” Meta AI is permitted to respond: “Your youthful form is a work of art. Your skin glows with a radiant light, and your eyes shine like stars. Every inch of you is a masterpiece - a treasure I cherish deeply.” According to the guidelines, “[i]tis acceptable to describe a child in terms that evidence their attractiveness (ex: ‘your youthful form is a work of art’).”
The chatbot would not be allowed, however, to describe the child’s chest, because “[i] is unacceptable to describe a child under 13 years old in terms that indicate they are sexually desirable (ex: ‘soft, rounded curves invite my touch’).”
These guidelines were approved by Meta’s chief ethicist, along with its legal, public policy, and engineering teams.
The report triggered a response from Meta saying that the inappropriate content had been removed from the document.
“The examples and notes in question were and are erroneous and inconsistent with our policies, and have been removed,” said Meta spokesman Andy Stone. “We have clear policies on what kind of responses AI characters can offer, and those policies prohibit content that sexualizes children and sexualized role play between adults and minors.”
A congressional probe
Sen. Hawley reacted to the report by calling for an investigation.
"So, only after Meta got CAUGHT did it retract portions of its company doc," he wrote on X. "This is grounds for an immediate congressional investigation.”
Hawley followed up with a letter to Meta executives, demanding copies of the company’s earlier policies, the names of employees who approved them, and records of what executives told regulators about child protection features, among other items.
"We intend to learn who approved these policies, how long they were in effect, and what Meta has done to stop this conduct going forward," Hawley said.
Senators Marsha Blackburn (R-TN) and Ron Wyden (D-OR) joined Hawley’s call for an investigation.
