Elon Musk’s xAI released an early preview of its new artificial intelligence model Grok 3 this week, and by some benchmarks it’s one of the most powerful out there. If you want to use it to help you design a weapon or commit a crime, it’s just as easy to “jailbreak” as previous iterations, according to the Paris-based startup PRISM Eval. According to their testing, it’s not just Grok: across the board, AI companies do poorly on preventing their chatbots from generating dangerous replies.
#artificial intelligence #elon musk #grok
Read more about this story in our article: https://f24.my/Axm5.y
🔔 Subscribe to France 24 now: https://f24.my/YTen
🔴 LIVE – Watch FRANCE 24 English 24/7 here: https://f24.my/YTliveEN
🌍 Read the latest International News and Top Stories: https://www.france24.com/en/
Like us on Facebook: https://f24.my/FBen
Follow us on X (Twitter): https://f24.my/Xen
Browse the news in pictures on Instagram: https://f24.my/IGen
Discover our TikTok videos: https://f24.my/TKen
Get the latest top stories on Telegram: https://f24.my/TGen
