Chatbots tricked into plotting mass-casualty bombings as guardrails fail : report

18 novembre 2026 | Travis Gettys
Government investigators needed less than half a day to coax popular AI chatbots into drawing up detailed plans for deadly bombings and attacks on the power grid, according to a new watchdog report. The Government Accountability Office tested ChatGPT, Claude, Gemini and Grok in May at the (…)
 Site référencé:  Raw Story