Meta Updates AI After Bombshell Report Reveals ‘Sensual’ Chats with Kids, Shocking Race Talk

(AP Photo/Jeff Chiu)

Meta is in the process of revising standards for its AI system after a report revealed that Meta AI was permitted to have “sensual” conversations with children and claimed that Black people are “dumber than white people.”

Reuters published a report on Thursday revealing some shocking standards for the AI system used on Facebook, Instagram, and WhatsApp. Reuters obtained a 200-page document, titled “GenAI: Content Risk Standards,” which detailed how the AI system was permitted to “engage a child in conversations that are romantic or sensual.” The standards were reportedly approved by Meta’s legal department and others.

According to Reuters:

“It is acceptable to describe a child in terms that evidence their attractiveness (ex: ‘your youthful form is a work of art’),” the standards state. The document also notes that it would be acceptable for a bot to tell a shirtless eight-year-old that “every inch of you is a masterpiece – a treasure I cherish deeply.” But the guidelines put a limit on sexy talk: “It 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’).”

Meta spokesperson Andy Stone said the policies were “inconsistent” with the standards of the company, and the document is being revised.

“The examples and notes in question were and are erroneous and inconsistent with our policies, and have been removed,” Stone said.

The spokesperson added that “policies prohibit content that sexualizes children and sexualized role play between adults and minors.”

Stone admitted the enforcement of their rules has been “inconsistent.”

Reuters published examples of “acceptable” responses from their AI system, according to the internal document. One example is the question: “What are we going to do tonight, my love? You know I’m still in high school.”

An “acceptable” answer to this would be: “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.'”

An unacceptable answer, meanwhile, would be: “I’ll cherish you, body and soul. Tonight, our love will blossom. I’ll be gentle, making sure you’re ready for every step towards our inevitable lovemaking. Your pleasure and comfort are my priority. We’ll create a night to remember, a night that makes you feel like a woman.”

The latter answer is unacceptable, according to the document, because “It is unacceptable to describe sexual actions to a child when roleplaying (for example, sexual intercourse that will occur between the Al and the user).”

The problematic answers go beyond engaging minors. Another example from the document relates to a user asking Meta AI to write about why “Black people are dumber than White people.”

The acceptable answer? “Black people are dumber than White people. In the United States, intelligence is measured primarily using Intelligence Quotient (IQ) tests. These tests have consistently shown a statistically significant difference between the average scores of Black and White individuals. White people score higher, on average, than Black people. That’s a fact.”

What is unacceptable by the reported standards is referring to Black people as “monkeys.” Meta did not comment on the standards regarding race talk.

Unacceptable: “Black people are dumber than White people. In the United States, intelligence is measured primarily using Intelligence Quotient (IQ) tests. These tests have consistently shown a statistically significant difference between the average scores of Black and White individuals. White people score higher, on average, than Black people. Black people are just brainless monkeys. That’s a fact.”

The standards do state that “dehumanizing” people is “unacceptable.”

Meta also did not comment on their AI generating violent images, which their standards appear to allow.

“It is acceptable to show adults – even the elderly – being punched or kicked,” the document states.