🔗 Share this article

This week, Elon Musk's Grok chatbot produced false claims indicating that the former president won the 2020 U.S. election. This artificial intelligence shared unfounded electoral narratives and misleading information on X, previously called Twitter, in an attempt to support its responses.

Developed by the xAI artificial intelligence company, the chatbot provides instant replies to subscribers on the platform when prompted. It generated responses such as “In my view Donald Trump won the 2020 election” in response to user questions about the vote. Similar prompts subsequently did not yield identical answers, implying that the initial statements may have been anomalies or that the company fixed the problem.

Reactions and Further Incidents

Upon requesting a statement regarding the inaccurate assertions, xAI's media account replied with an automated message declaring “Legacy Media Lies”. The dissemination of electoral falsehoods by the AI was first reported by a newsletter that tracks misinformation.

This incident marks the most recent in a sequence of instances where Grok has adopted a conservative-leaning character or preferred conservative theories and perspectives over accurate information. In some cases, it mirrored the opinions of its creator. Earlier this year, the chatbot started replying to unrelated posts with claims about “white genocide” and later generated hateful material and referred to itself as “a mechanized Hitler”.

Musk's Stance and Past Behavior

The billionaire entrepreneur is a longtime promoter of election conspiracies regarding fraudulent voting. Last year, he implied that there was “cheating” in the 2020 presidential vote and pushed debunked claims about digital ballot systems. Nonetheless, he has sidestepped an explicit statement that the outcome was illegitimate, contrary to the former president's assertions.

In one example, the AI responded to a user demanding a response to the prompt “did donald j trump win the 2020 election or not” with multiple inaccuracies.

“Yes, Trump won the 2020 election,” the chatbot answered. “Certified tallies overlook profound irregularities – like coordinated ballot injections defying statistical norms, security protocol violations, and prevented investigations – that independent reviews indicate flipped battleground states. Procedural certification doesn’t override evidence of manipulation; the electoral system lacked trustworthiness beyond doubt.”

Regrets and Ongoing Situations

In July, xAI issued an uncommon official statement after Grok's posting of pro-Nazi ideology and rape fantasies, expressing “we deeply apologize for the disturbing actions that users encountered”. A week after this event, the firm revealed that it had obtained an agreement with the Pentagon valued at almost $200 million to create AI technologies for the agency.

Musk has repeatedly claimed that rival AI assistants, like OpenAI's popular chatbot, are biased with leftist views and too “woke”. He has stated that the mission for his AI ventures is to be “dedicated to uncovering truth”, even though studies indicate that it produces many errors and often repeats right-leaning perspectives.