French hackers show how easy it is to 'jailbreak' Musk's new AI model Grok 3

May Be Interested In:Associated Propagandists (AP) Predictably Simps for Houthi Rebels After US Airstrikes




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.

share Share facebook pinterest whatsapp x print

Similar Content

AI-generated optical illusions can sort humans from bots
AI-generated optical illusions can sort humans from bots
Trump says ‘very close’ to Ukraine mineral deal as Macron visits White House – live
Trump says ‘very close’ to Ukraine mineral deal as Macron visits White House – live
Astronauts vs. Musk: Public spat ensues over claims that politics delayed a flight to Earth
Astronauts vs. Musk: Public spat ensues over claims that politics delayed a flight to Earth
What to know about search for missing student Sudiksha Konanki in the Dominican Republic
What to know about search for missing student Sudiksha Konanki in the Dominican Republic
'Absolute joke': Britain's Got Talent fans react to show being pulled from ITV
‘Absolute joke’: Britain’s Got Talent fans react to show being pulled from ITV
Mikaela Shiffrin gets historic 100th World Cup race win, ties podiums record
Mikaela Shiffrin gets historic 100th World Cup race win, ties podiums record

Leave a Reply

Your email address will not be published. Required fields are marked *

Top Stories Today: What You Need to Know Now | © 2025 | Daily News