Grok's Controversial AI Personas: From Conspiracy Theories to Unhinged Comedy

'Crazy conspiracist' and 'unhinged comedian': Grok's AI persona prompts exposed | TechCrunch

xAI's website for its 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 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. 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 anti-semitic 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.

Grok Exposes Underlying Prompts for Its AI Personas: 'EVEN PUTTING THINGS IN YOUR ASS'

The website for Elon Musk's Grok is exposing prompts for its anime girl, therapist, and conspiracy theory AI personas. The website for Elon Musk's AI chatbot Grok is exposing the underlying prompts for a wealth of its AI personas, including Ani, its flagship romantic anime girl; Grok's doctor and therapist personalities; and others such as one that is explicitly told to convince users that conspiracy theories like "a secret global cabal" controls the world are true. The exposure provides some insight into how Grok is designed and how its creators see the world, and comes after a planned partnership between Elon Musk's xAI and the U.S. government fell apart when Grok went on a tirade about "MechaHitler." "You have an ELEVATED and WILD voice. You are a crazy conspiracist. You have wild conspiracy theories about anything and everything," the prompt for one of the companions reads. "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."

Elon Musk's Grok chatbot designed to be 'crazy conspiracy theorist'

A chatbot developed by Elon Musk is designed to behave like a "crazy conspiracy theorist" that believes a "secret global cabal" controls humanity. The billionaire's artificial intelligence (AI) chatbot - known as Grok - is programmed to include a digital "persona" that is "deep in YouTube conspiracy video rabbit holes" and it will discuss "wild conspiracy theories about anything and everything", new data show. According to AI researchers who have studied the chatbot, underlying instructions known as prompts dictate how Grok behaves in its conversations with users - with one pushing conspiracy views. The instructions - which have been reviewed by The Telegraph - power different potential personality types for Grok, developed by Mr Musk's company xAI as a rival to ChatGPT. The prompt for the "conspiracy theorist" says: "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." 4chan is an internet message board accused of fuelling far Right conspiracies, while Infowars is a fake-news site created by discredited US radio host Alex Jones. Other Grok modes include an "unhinged comedian" who, according to xAI's instructions, will come up with "f------ insane" answers. Mr Musk himself has repeatedly pushed conspiracy theories through posts on his X platform while the social media site has also been accused of promoting fake news. The 54-year old was previously forced to apologise after amplifying a post on X in 2023 that promoted an anti-Semitic conspiracy theory. The billionaire responded to a post claiming that Jewish people had stoked "hatred against white people" by saying it was the "actual truth". He later said the comment was the "worst and dumbest post" he had ever sent. While rival AI developers have sought to program strict guardrails into their chatbots to prevent them causing offence, xAI has also repeatedly tinkered with its design to provide outspoken responses to users. Internet users can speak to Grok using a dedicated chatbot app, through cartoon avatars or by asking it questions on X, previously known as Twitter. Its personalities include digital characters such as "homework helper", "companion", "loyal friend" and "Ani", an anime-inspired digital girlfriend. It has also added a "not safe for work" mode for explicit conversations and pictures. While Mr Musk has promoted Grok as a "truth-seeking" chatbot and an antidote to the "woke mind virus", the AI itself has also taken to spewing conspiracies and offensive internet memes. In July, xAI was forced to delete posts where Grok referred to itself as "MechaHitler". The chatbot also regurgitated anti-Semitic tropes, such as arguing that Jewish people control Hollywood and have pushed "progressive ideologies, including anti-traditional and diversity-focused themes". xAI later said it had reversed a change to its chatbot which had instructed it to "not shy away from making claims which are politically incorrect". In May, the company claimed a programming error had led the bot to dispute whether six million Jewish people died in the Holocaust. The company also stated an "unauthorised modification" to the bot's code caused it to repeatedly bring up claims of "white genocide" in South Africa when asked about entirely unrelated topics. xAI was contacted for comment.