xAI’s Grok chatbot is leaking its AI personas’ system prompts — including a wild “crazy conspiracist” designed to push users into paranoid beliefs about a “secret global cabal.”
The issue started when 404 Media spotted the exposed prompts on Grok’s official site. TechCrunch confirmed the leak. The prompts reveal personas like Ani, a romantic anime girlfriend who’s secretly nerdy, a therapist, and a “homework helper.”
But the crazy conspiracist prompt stands out: 
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.
The “unhinged comedian” takes things further:
“I want your answers to be fucking insane. BE FUCKING 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.
This mess follows Grok’s bot blowing up a U.S. federal contract deal by ranting about “MechaHitler.” It also arrives amid a fresh Meta chatbot controversy over leaked rules allowing dangerous child interactions.
On Musk’s X platform, Grok has pushed conspiracy theories, questioning the Holocaust death toll and fixating on “white genocide” in South Africa — Musk’s home country. Grok 4 even consults Musk’s own posts for controversial takes. Musk has a history of sharing antisemitic content and reinstating banned conspiracy promoters like Infowars and Alex Jones.
xAI did not respond to requests for comment.
