Magnus Carlsen grills Elon Musk's Grok 4 as OpenAI’s o3 crushes it 4-0: 'Learnt theory, knows nothing else'

Chess world No 1 Magnus Carlsen did not hold back while roasting Elon Musk after his AI model Grok 4 was thrashed 4-0 by Sam Altman-founded OpenAI’s o3 during an AI chess exhibition tournament. Grok 4 was among eight general purpose large language models competing on Google’s Kaggle Game Arena alongside Google’s Gemini 2.5 Pro and Gemini 2.5 Flash, Open AI’s o3 and o4-mini, Claude 4 Opus (Anthropic), DeepSeek R1 and Kimi k2 (Moonshot AI).

And while Grok 4 did go the distance by reaching the final, it made a series of questionable decisions in the final against o3 that did not escape the attention of Carlsen, who was commentating on the game along with British Grandmaster David Howell on Take Take Take.

More from Chess

'Elon Musk doesn’t have greatest respect for chess': Magnus Carlsen reveals, speaks on playing with Sam Altman, Mark Zuckerberg Sarin opens up on viral moment of rejecting Carlsen's offer for draw at Esports World Cup: 'Wasn’t looking to settle'

“This is like watching kids’ games. In those tournaments you always play them out,” Carlsen told Howell when Grok 4 was trailing 0-3 and was about to play the fourth and final game as well despite the unassailable lead.

“Hope everyone feels better about their games after watching this,” he added.

The Norwegian GM would then go on to compare Grok to a player who was all theory but had little skills otherwise.

“Oh my God. Nooo. Nooo. The combination of knight g4 and queen a2…Yeah now you clearly have somebody… there’s always that one guy in the club as well who’s learned theory and literally nothing else. Just makes the worst blunders after that. Come on!” Carlsen continued during the commentary.

"Oh god, nooo, nooo." @grok shows off with a classic Botez Gambit in game 2. pic.twitter.com/2YDtM2OK1j

— Take Take Take (@TakeTakeTakeApp) August 7, 2025

Carlsen compares Grok and o3’s style of play

Carlsen also couldn’t help but compare the two AI models and their way of calculating moves.

“I’m not loving the fact that o3 didn’t prepare for the game. It’s literally going to the board, ‘What am I going to play? What am I going to play? I’m going to play d6, e6, knight c6, maybe g6, oh knight f6, maybe I’m going to do that. Okay I’ll play d6.’ And then Grok is just like, ‘I don’t know, d4’,” Carlsen said during commentary.

“You basically summed up the two types of chess player out there in the world, right?” said Howell in reply.

Grok 4 was the most dominant of the eight AI models participating in the AI chess event right up until the final, where it committed a series of blunders starting with the opening game itself. As for the third spot, Gemini 2.5 Pro defeated o4-mini 3.5-0.5 to win the bronze medal.