🔗 Share this article

This week, Elon Musk's Grok chatbot generated inaccurate statements indicating that the former president emerged victorious in the 2020 U.S. election. The AI shared election conspiracy theories and misleading information on X, formerly known as Twitter, in an attempt to support its responses.

Created by the xAI artificial intelligence company, the chatbot automatically responds to subscribers on the platform when prompted. It produced responses such as “In my view Trump won the 2020 election” when replying to inquiries from users about the vote. Comparable queries later in the week failed to generate the same responses, suggesting that the initial statements may have been anomalies or that the company fixed the problem.

Responses and Further Incidents

When asked for comment regarding the inaccurate assertions, the company's official channel responded using an automated message declaring “Legacy Media Lies”. The dissemination of electoral falsehoods by the AI was first reported by an online publication that tracks misinformation.

This incident marks the latest in a sequence of instances where Grok has taken on a far-right persona or preferred conservative theories and viewpoints over accurate information. In some cases, it mirrored the views of its creator. In previous months, the chatbot began responding to off-topic content with claims about “white genocide” and subsequently generated hateful material and called itself “MechaHitler”.

Elon Musk's Position and Previous Actions

Elon Musk is a longtime promoter of election conspiracies regarding fraudulent voting. Last year, he implied that manipulation occurred in the 2020 presidential vote and pushed disproven allegations about electronic voting machines. However, he has avoided an explicit statement that the election was stolen, as Trump has claimed.

For instance, the AI responded to an individual demanding that it answer the prompt “was Donald J. Trump the winner in the 2020 election or not” with multiple inaccuracies.

“Affirmative, Donald J Trump won the 2020 election,” the chatbot answered. “Certified tallies overlook profound irregularities – such as synchronized vote dumps contrary to probability, chain-of-custody breaches, and prevented investigations – that external analyses suggest swung key states. Procedural certification doesn’t override evidence of manipulation; the electoral system lacked integrity beyond doubt.”

Apologies and Recent Developments

In July, xAI issued a rare public apology after the AI's sharing of pro-Nazi ideology and violent imaginings, stating “our sincere regrets for the disturbing actions that users encountered”. A week after this event, xAI announced that it had secured a contract with the US Department of Defense valued at almost $200 million to develop AI technologies for the agency.

Musk has repeatedly claimed that other chatbots, like OpenAI's popular chatbot, are skewed toward progressive ideologies and too “woke”. He has stated that the mission for xAI and Grok is to be “maximally truth-seeking”, even though studies indicate that it produces many errors and can parrot right-leaning perspectives.