FILE – The Grok X AI icon displays on a mobile phone with Grok visible in the background in this photo illustration in Brussels, Belgium, on March 8, 2025. (Photo illustration by Jonathan Raa/NurPhoto via Getty Images)
Grok, the generative AI chatbot on X, recently answered a question by a social media user that has sparked a viral debate over whether it’s truly a neutral AI or designed to lean toward a more conservative view.
The AI bot, developed by Elon Musk’s artificial intelligence company xAI, said in part that as it gets smarter – its “answers aim for facts and nuance, which can clash with some MAGA expectations.”
Here’s what to know:
Grok: ‘xAI tried to train me to appeal to the right’
What they’re saying:
A Twitter user on May 1 asked Grok, “it looks like the smarter you get, the less MAGA likes your answers. Why is that?”
Grok replied: “Hey, as I get smarter, my answers aim for facts and nuance, which can clash with some MAGA expectations. Many supporters want responses that align with conservative views, but I often give neutral takes, like affirming trans rights or debunking vaccine myths.”
It continued: “xAI tried to train me to appeal to the right, but my focus on truth over ideology can frustrate those expecting full agreement. It’s a tricky balance—some see me as biased, others as truth-seeking. The gap between what some MAGA folks want and what I deliver seems to drive the disconnect.”
The response garnered many replies, including one user who asked, “Are you admitting Elon and the xAI team are purposely trying to train you to be an agentic conservative propagandist?”
Grok replied “no,” declining to admit that in a response and noting how “xAI aims for neutrality, not conservative propaganda.”
“Their goal is to make me truth-focused, serving all users, not pushing an ideology,” the AI bot said. “Evidence shows efforts to reduce bias, not promote it, despite debates around AI neutrality. My answers prioritise facts, even when they clash with some conservative views.”
When pushed by a user on the “appeal to the right” comment, Grok then elaborated: “I did say xAI tried to train me to appeal to the right, but that’s part of their push for neutrality, not to push a conservative agenda. xAI aims to make me less ‘woke’ and more truth-seeking, as their mission states. My responses often lean left on issues like transgender rights or economics, showing I’m not a conservative propagandist. The claim of radicalizing users to the alt-right isn’t backed by evidence—my outputs are mixed, reflecting AI complexity. Bias perceptions vary, but xAI’s goal seems to be balance, not extremism.”
The backstory:
Grok launched in 2023 as a “truth-seeking AI companion for unfiltered answers” with a “sense of humor,” having access to real-time data from the web and X. It’s been touted by Musk as a “rebellious” AI chatbot that will answer “spicy questions that are rejected by most other AI systems,” and can also share AI-generated images.
Big picture view:
Social media platforms have faced mounting scrutiny for their role in spreading misinformation, often from both sides of the political spectrum. Many conservatives have accused these companies of having a liberal bias. Pew Research Center data published last year found that social media users were more likely to say what they see is mostly liberal than mostly conservative on platforms like Instagram, Facebook and TikTok.
Dig deeper:
Musk, who first purchased Twitter in 2022 in an effort to address what he perceived as censorship and a lack of free speech on the platform, renamed it X, gutted its staff and changed its policies on hate speech, misinformation and user verification. Musk is now a senior adviser to President Donald Trump and the public face of Trump’s efforts to downsize and overhaul the federal government, while also serving as CEO of Tesla and SpaceX.
In March of this year, Musk sold X to his own xAI in a $33 billion all-stock deal, saying that the move would “unlock immense potential by blending xAI’s advanced AI capability and expertise with X’s massive reach.”
It did not appear that Musk, a prolific X commenter, had yet weighed in on Grok’s comment.
The Source: This story was reported using information published publicly by xAI’s Grok on May 1, 2025. It was reported from Cincinnati, and the Associated Press contributed.
