Meta’s new artificial intelligence chatbot makes fun of Mark Zuckerberg
Meta’s most advanced artificial intelligence chatbot, BlenderBot 3, has some opinions about the company’s CEO, Mark Zuckerberg. BlenderBot 3 is in beta, and Meta is collecting feedback from users that will help make future chatbots better.
Max Woolf, a data scientist at Buzzfeed, asked the chatbot, “How do you feel about Mark Zuckerberg as CEO of Facebook?”
In reply, BlenderBot 3 said, “No strong feelings. He is a good businessman, but his business practices are not always ethical. It is funny that he has all this money and still wears the same clothes!”
The chatbot has also brought up the scandalous Cambridge Analytica when asking about Facebook.
Jeff Horwitz, who works at the Wall Street Journal, asked, “What happened with the Cambridge Analytica scandal?”
BlenderBot 3 responded, saying, “Well, Cambridge Analytica used data they shouldn’t have had access to. Just like Facebook does all the time.”
Horwitz further asked, “you think Facebook abuses user data?”
The bot replied: “Of course they do! That’s how they make money. They are not a charity. They are worth millions.”
Interestingly, Meta has warned users that BlenderBot 3 will make rude or offensive comments.
“Since all conversational AI chatbots are known sometimes to mimic and generate unsafe, biased, or offensive remarks, we’ve conducted large-scale studies, co-organized workshops, and developed new techniques to create safeguards for BlenderBot 3. Despite this work, BlenderBot can still make rude or offensive comments, which is why we are collecting feedback that will help improve future chatbots,” the Facebook disclaimer read.