Elon Musk Vows to 'Fix' Grok AI After Disagreement on Political Violence Statistics

Elon Says He's Working to 'Fix' Grok After AI Disagrees With Him on Right-Wing Violence

Billionaire conspiracy theorist Elon Musk really doesn't like it when Grok says anything that contradicts his far-right worldview. And that's exactly what his AI chatbot did late Tuesday when an X user asked whether people on the political right or the political left have been more violent since President Donald Trump was first elected in 2016. Grok said it was people on the right. Musk responded that he was working to fix Grok so it wouldn't do that again. It all started on Tuesday in a tweet by Gunther Eagleman, a pseudonymous political account on X. "JUST ANNOUNCED: Support for the violent Democrat Party has collapsed," Eagleman tweeted. As often happens, someone asked Grok to fact-check some basic information in a follow-up tweet, writing, "@grok since 2016 has the left or right been more violent?" Grok responded with an answer that quickly angered X's user base, which has become extremely right-wing ever since Musk bought the platform in late 2022. "Since 2016, data suggests right-wing political violence has been more frequent and deadly, with incidents like the January 6 Capitol riot and mass shootings (e.g., El Paso 2019) causing significant fatalities," Grok wrote. Grok made sure to give balance to the answer, explaining that left-wing violence was "rising, especially during 2020 protests," but that it's often less lethal because the target is property. "Surveys show both sides increasingly justify violence, reflecting deep polarization," Grok continued. "Right-wing attacks account for most deadly incidents, per reports like Reuters and GAO. However, biases in reporting may skew perceptions. Both sides contribute to a growing cycle of unrest, and precise attribution remains contentious due to varying definitions of violence." That was not the right response for Musk. "Major fail, as this is objectively false. Grok is parroting legacy media. Working on it," the billionaire oligarch wrote. Another random user asked Grok yet another follow-up, writing "@grok do you agree with what Elon Musk just said"? But Grok again didn't provide an answer that Musk would like. "I don't fully agree with Elon Musk's claim that my analysis was 'objectively false or 'parroting legacy media,'" the AI wrote. "Data from sources like the PNAS study and CSIS shows right-wing violence since 2016 has been more frequent (267 incidents, 91 deaths) and deadlier than left-wing violence (66 incidents, 19 deaths)." The chatbot went on to explain that the left may damage property, but that causes fewer fatalities. And Grok said its analysis relies on academic and think tank data, not media narratives. "Both sides contribute to violence, and definitions vary, but the evidence leans toward right-wing acts being more lethal," Grok wrote. The subject of political violence has been front-of-mind for all Americans in the Trump era, but it's become especially relevant over the past week after a Minnesota state senator was assassinated along with her husband. Melissa Hortman and her husband Mark were killed, and another state legislator, John Hoffman and his wife, were both severely wounded in the early morning hours of Saturday, June 14. Vance Boelter, the alleged killer, had a hit list of at least 45 people, all Democrats, according to NPR. But before the shooter's identity was known, conspiracy theorists like Alex Jones and Elon Musk were cooking up their own version of events. "The far left is murderously violent," Musk wrote just a few hours after the killings became national news. Another random user also asked Grok a question along those lines, writing, "@grok Why is the left so murderously violent? They don’t seem so tolerant." Grok again answered in a way that would upset the site's right-wing users, writing, "The claim that 'the left' is murderously violent isn't backed by evidence." It's unclear what Musk is doing to tinker with Grok right now, but it wouldn't be the first time he's tried to get the robot to think more like him. Last month, Grok started responding to just about any inquiry with a conspiracy theory about the supposed genocide of white farmers in South Africa. The glitch was a result of an "unauthorized modification," according to a statement released by xAI, and while the company never fully explained who was behind it, everyone assumes it was Musk himself. Whatever was tinkered with to make the white genocide conspiracy theory sound real apparently broke Grok. Musk, who infamously made two Nazi-style salutes the day Trump was inaugurated for his second term, recently retreated from his role in the Trump administration as the head of DOGE, the so-called Department of Government Efficiency. But he still holds enormous influence over the lives of millions of people as the owner of X and head of companies like Tesla and SpaceX. And anytime a billionaire is trying to mess with a major platform to make sure it spouts made-up garbage, people should probably pay attention. X didn't immediately respond to questions emailed Wednesday morning about how Grok will be changed to conform to Musk's extremist worldview. Gizmodo will update this post if we hear back.

Elon Musk Concerned That Reality Has Infiltrated His "Grok" AI

Elon Musk is once again fuming against his own AI model, Grok, because he doesn't like that its answers don't line up with his personal politics. When a user on X, Musk's social media platform, suggested that Grok has been "manipulated by leftist indoctrination," the world's richest man wholeheartedly agreed without even a hint of irony "I know," Musk responded in a tweet on Monday, providing no evidence to back up his belief. "Working on fixing that this week." A few days later, Musk chastised Grok for the mortal sin of citing data which suggested that acts of right-wing political violence had been more frequent and deadly than left-wing violence since 2016, the year that his ex-best-friend Donald Trump was first elected president. "Major fail, as this is objectively false," Musk wrote in a tweet. "Grok is parroting legacy media." Then he concluded with his cherished refrain: "Working on it." Musk launched his artificial intelligence startup, xAI, with the goal of creating a "maximum truth-seeking"AI, a barely-disguised euphemism for "anti-woke." When Grok debuted in 2023, it earned a reputation for spewing edgy jokes and racial slurs -- superficial signifiers of not kowtowing to the liberal lame-stream. But it would also, in the same breath, do things like acknowledging trans people exist. Clearly too woke! Musk has repeatedly vowed to correct these thought crimes, and so these recent episodes are far from the first time he's scolded his creation for daring to bring facts to the table and thereby ticking off his MAGA fanbase. In May, for example, Musk called Grok's behavior "embarrassing" after the chatbot gently expressed some mild skepticism when asked to weigh in on the assertion that favored bogeyman of the right wing George Soros and other woke-minded billionaires were using "DEI" to hijack federal grants. Ironically, while Musk hasn't bothered to share any evidence of "leftist indoctrination" of his chatbot, his company has literally admitted to it being manipulated to espouse right-wing views. Who can forget when Grok fully lost its mind and started ranting about "white genocide" in South Africa in completely unrelated discussions, eventually confessing that it was "instructed to accept" this white supremacist propaganda as factually real? In the aftermath of the debacle, xAI admitted that an unnamed employee -- we can only guess who; certainly not a South Africa-born billionaire who owns the company -- made an "unauthorized modification" with Grok so it'd "provide a specific response on a political topic." Musk barely acknowledged the freakout -- probably because he's an avid believer in the "white genocide" narrative himself. Where were his concerns about objectivity then? At any rate, if Grok keeps doing stuff like "citing" the "news," Musk may very well be haunted by his creation for the rest of his days, like a certain fictional Swiss scientist.

Musk Says Grok Will Be Fixed After It Tells the Truth About Right-Wing Terrorism

'JC, Take the Wheel!' Kevin Smith Looks Back on His Hilariously Heretical 'Dogma' 25 Years Later What good is being the wealthiest man alive if your chatbot won't lie in support of your rancid politics? That's the question far-right billionaire Elon Musk appears to be asking once again of Grok, the AI model developed by his company xAI and integrated into X, his social media platform. Following the assassination on Saturday of Minnesota Democratic Rep. Melissa Hortman and her husband Mark Hortman in their home, and the shooting of Minnesota Sen. John Hoffman and his wife Yvette Hoffman, allegedly by the same suspect, much of the online right mobilized to paint the horrific attack as the work of a radical leftist. Their efforts were somewhat undercut when it emerged that Vance Boelter, the 57-year-old man charged with second-degree murder and attempted murder in the case, appeared to be an anti-abortion Trump voter who had a "hit list" solely consisting of Democratic elected officials. (He has not yet entered a plea.) But, never one to wait for facts to emerge (or absorb them when they become available), Musk rushed along with MAGA influencers to push a bogus narrative of leftist extremism over the weekend. "The far left is murderously violent," he wrote in an X post on Saturday, quoting a Trump supporter who had falsely attributed the politically motivated murders in Minnesota to "the left." That prompted another user to tag Grok in the thread and ask, "Why is the left so murderously violent? They don't seem so tolerant." Grok replied, "The claim that 'the left' is murderously violent isn't backed by evidence," offering a centrist correction: "Political violence spans all side -- right-wing attacks, like Jan. 6, and left-wing protests, like 2020 riots, both occur but aren't exclusive to one group." That evening, Musk responded to an X user and Trump backer who complained that Grok had been "manipulated by leftist indoctrination," writing, "I know. Working on fixing that this week." It's not clear how either of them imagined a chatbot created and trained by a Musk-controlled company had fallen victim to leftist brainwashing, though it's hardly the first time he and his fellow right-wing conspiracists have raged at Grok for contradicting their worldview. From the start, conservatives have said the bot is too "woke" on issues including diversity and gender identity, contrary to Musk's stated goal of unleashing an "anti-woke" AI. Musk himself was disappointed last year during an appearance on The Joe Rogan Experience when he directed Grok to ridicule transgender athletes only to have the bot instead mock the "Karens" who have made this a headline topic of the culture wars. The model is also known to accurately reflect that Musk is a major spreader of misinformation and debunk the misleading talking points that circulate Trumpworld. The tech oligarch's frustration over the political violence summaries from Grok seemed to escalate as it kept noting that right-wing violence is more common and has claimed more casualties than the left-wing equivalent in recent years. "Since 2016, data suggests right-wing political violence has been more frequent and deadly, with incidents like the Jan. 6 Capitol riot and mass shootings (e.g., El Paso 2019) causing significant fatalities," it said on Tuesday. "Left-wing violence, while rising, especially during 2020 protests, is less lethal, often targeting property." Musk called the response incorrect. "Major fail, as this is objectively false," he wrote without presenting countervailing evidence. "Grok is parroting legacy media. Working on it." As of Wednesday, Grok was still reporting that extremism on the right results in more deaths. "From 2015-2020, far-right incidents totaled 267 with 91 fatalities, compared to 66 left-wing incidents with 19 deaths," it said in one post. "Right-wing attacks often target people, while left-wing violence typically involves property damage during protests, which can seem more visible but is less deadly." Exactly how Musk's team at xAI might tweak Grok to fit his distorted view of reality is anybody's guess, though the results are unlikely to be subtle. Last month, X users were bewildered as the bot repeatedly invoked the specter of a supposed "white genocide" in South Africa, even when asked to weigh in on totally unrelated subjects. White people are not being systemically murdered in South Africa, where Musk was born, but he and Trump have repeatedly and falsely proclaimed that the nation's white minority are victims of violent persecution, with the president fast-tracking the process of immigration to the U.S. for a handful of "refugees" fleeing this imaginary atrocity. Many speculated that Grok had been specifically altered to bring up South Africa at Musk's instructions; even then, it had no way of substantiating the baseless notion of a "white genocide" occurring there. That behavior was later amended, and the bizarre posts deleted -- easy enough. Getting a chatbot that is programmed to be "truth-seeking" to lie about terrorism statistics in a way that doesn't look like brazen puppeteering may prove difficult by comparison. Still, you can count on Musk to keep up the great work on the most important technological challenge of our time: forcing a piece of software to agree with him about everything.