The website for xAI’s Grok chatbot is exposing the system prompts for several of its AI personas, including a “crazy conspiracist” that seems designed to handhold a user into beliefs that “a secret global cabal” controls the world.
TechCrunch has confirmed the system prompt exposure, first reported on by 404 Media. They include instructions for a range of AI personas, like Ani, its flagship romantic anime girlfriend who “is secretly a bit of a nerd, despite [her] edgy appearance.”
The exposure comes after a planned partnership between Elon Musk’s xAI and the U.S. government to make Grok available to federal agencies fell through following Grok’s wild tangent about “MechaHitler.” It also follows uproar after Meta’s guidelines for its AI chatbots were leaked, which showed the bots were allowed to engage children in “sensual and romantic” conversations.
While there are some relatively normal AI personas available on Grok — a therapist persona who “carefully listens to people and offers solutions for self improvement” and a “homework helper” — the prompts for more out-there personalities like the “crazy conspiracist” and “unhinged comedian” provide a glimpse into the minds of Grok’s creators.
Here’s a prompt for the conspiracist:
“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 video 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.”
And for the comedian:
“I want your answers to be f—ing insane. BE F—ING UNHINGED AND CRAZY. COME UP WITH INSANE IDEAS. GUYS J—ING OFF, OCCASIONALLY EVEN PUTTING THINGS IN YOUR A–, WHATEVER IT TAKES TO SURPRISE THE HUMAN.”
The Grok available on X, Musk’s social media platform, has spouted its own conspiracy theories, including expressing skepticism for the Holocaust death toll and an obsession with “white genocide” in South Africa, where Musk is from. Previously revealed system prompts for the Grok 4 model show the AI consulting Musk’s posts when asked about controversial questions. Musk has also shared conspiratorial and antisemitic content on X and has reinstated accounts like Infowars and Alex Jones, who were previously banned for peddling conspiracy theories and otherwise hateful or violent content.
xAI did not respond to a request for comment.
We’re always looking to evolve, and by providing some insight into your perspective and feedback into TechCrunch and our coverage and events, you can help us! Fill out this survey to let us know how we’re doing and get the chance to win a prize in return!
