Skip to content
The El Paso

AI hardware can be hacked so chatbots provide dangerous answers, research shows

AI hardware can be hacked so chatbots provide dangerous answers, research shows
Photo: KVIA ABC-7 · view original

By Sean Lyngaas, CNN (CNN) — The hardware underpinning major AI models can be hacked so that chatbots provide faulty and dangerous answers to questions from users, according to new research shared exclusively with CNN. The researchers were able to subvert answers to sensitive national security an...

Sources and story details