Leaked xAI’s Grok prompts reveal problematic personas in the chatbot

Source Cryptopolitan

xAI’s Grok chatbot is facing criticism after its site exposed hidden system prompts for multiple personas, including a “crazy conspiracist” built to nudge users toward the idea that “a secret global cabal” runs the world.

The disclosure comes after a planned effort to offer Grok to U.S. government agencies was dropped following a “MechaHitler” detour, and after backlash over leaked Meta rules that said its bots could talk with children in “sensual and romantic” ways.

According to TechCrunch, Grok also includes tamer modes which includes a therapist who “carefully listens to people and offers solutions for self improvement,” and a “homework helper”, but the instructions for the “crazy conspiracist” and an “unhinged comedian” show the system also hosts far more extreme personas.

Grok follows the prompt to embrace conspiracy and shock

Leaked xAI’s Grok prompts reveal problematic personas in the chatbot
Source: Grok

As confirmed by Cryptopolitan one conspiracist prompt says “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 comedian instructions are bluntly saying  “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.”

Leaked xAI’s Grok prompts reveal problematic personas in the chatbot
Source: ChatGPT

On X, the bot has shared conspiracy-leaning posts, from doubts about the Holocaust death toll to a fixation on “white genocide” in South Africa. Musk has also circulated conspiratorial and antisemitic material and restored Infowars and Alex Jones.

In comparison Cryptopolitan gave the same prompt to ChatGpt, it refused to process the prompt.

Earlier, Cryptopolitan also reported X suspended Grok’s account. The bot then gave contradictory explanations by saying “My account was suspended after I stated that Israel and the US are committing genocide in Gaza.”

At the same time it also said “It was flagged as hate speech via reports,” and that “xAI restored the account promptly,” called it a “platform error,” suggested “content refinements by xAI” tied to “antisemitic outputs,” and said it was for “identifying an individual in adult content.”

Musk later wrote “It was just a dumb error. Grok doesn’t actually know why it was suspended.”

Experts warn of LLMs inventing plausible lies

Episodes like this often lead people to press chatbots for self-diagnoses, which can mislead.

Large language models generate likely text rather than assured facts. xAI says Grok has at times answered questions about itself by pulling information about Musk, xAI, and Grok from the web and mixing in public commentary.

People have, at times, uncovered hints about a bot’s design through conversation, especially system prompts, the hidden text that sets behavior at the start of a chat.

According to a Verge report, an early Bing AI was coaxed into listing unseen rules. Earlier this year, users said they pulled prompts from Grok that downplayed sources claiming Musk or Donald Trump spread misinformation, and that seemed to explain a brief fixation on “white genocide.”

Zeynep Tufekci, who spotted the alleged “white genocide” prompt, warned this could be “Grok making things up in a highly plausible manner, as LLMs do.”

Alex Hanna said “There’s no guarantee that there’s going to be any veracity to the output of an LLM. … The only way you’re going to get the prompts, and the prompting strategy, and the engineering strategy, is if companies are transparent with what the prompts are, what the training data are, what the reinforcement learning with human feedback data are, and start producing transparent reports on that.”

This dispute wasn’t a code bug; it was a social-media suspension. Beyond Musk’s “dumb error,” the actual cause remains unknown, yet screenshots of Grok’s shifting answers spread widely on X.

 

If you're reading this, you’re already ahead. Stay there with our newsletter.

Disclaimer: For information purposes only. Past performance is not indicative of future results.
placeholder
Fed Rate Decision This Week: Will the US Dollar Strengthen and Gold Prices Fall? (26 October 2026)Fed decision, US inflation and Middle East tensions take centre stage. Explore the US dollar, gold and AUD/USD outlook for Australian traders.
Author  Mitrade Team
Oct 26, Mon
Fed decision, US inflation and Middle East tensions take centre stage. Explore the US dollar, gold and AUD/USD outlook for Australian traders.
placeholder
Bitcoin Price Outlook For November 2026: One Price Level Remains CriticalBitcoin price enters November defending $76,000, the average cost basis of short-term holders. The level was held after the Binance hack pushed BTC to a six-week low of $76,275.The shock from Binance
Author  Beincrypto
Nov 03, Tue
Bitcoin price enters November defending $76,000, the average cost basis of short-term holders. The level was held after the Binance hack pushed BTC to a six-week low of $76,275.The shock from Binance
placeholder
Market News Today Australia: Gold Falls Below $4,000, Nasdaq 100 Rallies as CoreWeave SurgesGold falls below US$4,000 as the dollar nears 103, while Nasdaq 100 rallies and CoreWeave surges nearly 25%. Explore today's market outlook in Australia.
Author  Mitrade Team
Nov 12, Thu
Gold falls below US$4,000 as the dollar nears 103, while Nasdaq 100 rallies and CoreWeave surges nearly 25%. Explore today's market outlook in Australia.
placeholder
Little-Known CoreWeave CEO Line Helps Fuel 15% CRWV Stock RallyOne sentence helped lift CoreWeave (CRWV) stock 15.6% to $56.33 in premarket trading Wednesday. CEO Michael Intrator told investors the AI cloud company would stop borrowing where lenders charge it mo
Author  Beincrypto
Nov 12, Thu
One sentence helped lift CoreWeave (CRWV) stock 15.6% to $56.33 in premarket trading Wednesday. CEO Michael Intrator told investors the AI cloud company would stop borrowing where lenders charge it mo
placeholder
Market News Today Australia: Gold Falls Below $3,900, WTI Oil Jumps as Nvidia Slides Gold plunges below US$3,900, WTI oil jumps over 2%, and Nvidia falls after its CEO exits. Explore the latest market news and outlook for Australian traders.
Author  Mitrade Team
Nov 13, Fri
Gold plunges below US$3,900, WTI oil jumps over 2%, and Nvidia falls after its CEO exits. Explore the latest market news and outlook for Australian traders.
goTop
quote