Elon Musk is starting to see the fruits of his AI shopping spree with the release of Grok 3, one of the most capable AI models yet. But according to French startup PRISM Eval, the chatbot’s safety filters can easily be bypassed to make requests about dangerous and illegal activities, such as building a bomb or hiding a body.

Source: https://www.france24.com/en/tv-shows/tech-24/20250221-french-hackers-show-how-easy-it-is-to-jailbreak-musk-s-new-ai-model-grok-3