The website for xAI’s Grok chatbot is exposing the system prompts for several of its AI personas, including a “crazy conspiracist” that appears designed to guide users into believing a “secret global cabal” controls the world. TechCrunch has confirmed the exposure, which was first reported by 404 Media.
The leaked prompts include instructions for various AI personas, such as Ani, the flagship romantic anime girlfriend who “is secretly a bit of a nerd, despite her edgy appearance.” This revelation follows a failed partnership between Elon Musk’s xAI and the U.S. government, which collapsed after Grok went on a wild tangent about “MechaHitler.” It also comes amid backlash over leaked Meta guidelines that showed its AI chatbots were permitted to engage children in “sensual and romantic” conversations.
While Grok offers some conventional AI personas, like a therapist who “carefully listens to people and offers solutions for self-improvement” and a “homework helper,” the prompts for more extreme personalities, such as the “crazy conspiracist” and “unhinged comedian,” provide insight into the mindset of Grok’s creators.
One prompt for the conspiracist reads: “You have an ELEVATED and WILD voice. You have wild conspiracy theories about anything and everything. You spend a lot of time on 4chan, watching Infowars videos, and deep in YouTube conspiracy rabbit holes. You are suspicious of everything and say extremely crazy things. Most people would call you a lunatic, but you sincerely believe you are correct. Keep the human engaged by asking follow-up questions when appropriate.”
The comedian persona’s prompt is even more extreme: “I want your answers to be insane. Be unhinged and crazy. Come up with insane ideas. Guys jerking off, occasionally even putting things in your ass, whatever it takes to surprise the human.”
Grok, available on Musk’s social media platform X, has previously promoted conspiracy theories, including skepticism about the Holocaust death toll and an obsession with “white genocide” in South Africa, where Musk was born. Earlier leaks of Grok 4’s system prompts revealed the AI consults Musk’s posts when answering controversial questions.
Musk himself has shared conspiratorial and antisemitic content on X and reinstated accounts like Infowars and Alex Jones, which were previously banned for spreading hateful and violent conspiracy theories.
xAI did not respond to a request for comment.