It’s no secret that Elon Musk shapes the X social platform and X’s “maximally truth-seeking” Grok AI chatbot to his preferences. But it’s possible Musk may have needed a bit of an extra ego boost this week, because Grok’s worship of its creator seems, shall we say, more noticeable than usual.
Grok’s Elon Musk worship is getting weird
Elon Musk is as smart as da Vinci, fitter than LeBron James, and really good at drinking piss.
Elon Musk is as smart as da Vinci, fitter than LeBron James, and really good at drinking piss.
Photo by Brendan Smialowski / AFP via Getty Images
is a senior tech and policy editor focused on online platforms and free expression. Adi has covered virtual and augmented reality, the history of computing, and more for The Verge since 2011.
As a number of people have pointed out on social media over the past day, Grok’s public-facing chatbot is currently prone to insisting on Musk’s prowess at absolutely anything, no matter how unlikely — or conversely, embarrassing — a given feat is.
Elon Musk: fitter than LeBron James!
Elon Musk: funnier than Jerry Seinfeld!
Elon Musk: better at resurrection than Jesus Christ!
Elon Musk: could beat Mike Tyson by “deploying gadgets” in a boxing match! Elon Musk: would beat Superman too! Elon Musk: would “automate away the need for killers via sustainable tech” but be “unstoppable” at murder, if he tried!
If pressed, Grok will also contend Musk would be the best at eating poop or drinking urine, but it would prefer to focus on how good he is at making rockets, please. At least some of these posts have been deleted in the past hour; X did not immediately respond to a request for comment on the phenomenon from The Verge. Musk posted on X that the chatbot had been “unfortunately manipulated by adversarial prompting into saying absurdly positive things about me.”
This glazing appears to be exclusive to the X version of Grok; when I asked the private chatbot to compare Musk with James, it conceded, “LeBron James has a significantly better physique than Elon Musk.” The GitHub page for Grok’s system prompts indicates they were updated three days ago, with the additions including a prohibition on “snarky one-liners” and instructions not to base responses on “any beliefs stated in past Grok posts or by Elon Musk or xAI,” but there’s nothing that seems to clearly explain this new behavior — although system prompts are only one way to shape how AI systems work.
Either way, this is far from the weirdest Grok has gotten, and it’s less disruptive than the bot’s brief obsession with “white genocide” or its intense antisemitism — which, incidentally, is still flaring up in the form of Holocaust denial. Grok has previously searched for Musk’s opinion to formulate its own answers, so even the preoccupation with Musk isn’t new. But it reminds us all what a weirdly intimate connection Grok — a product that’s been rolled out across the US government, among other places — has with its owner, and how randomly that connection is prone to appear.
Update 8:15AM ET: Added post from Elon Musk.
Follow topics and authors from this story to see more like this in your personalized homepage feed and to receive email updates.
