US govt says it got ChatGPT, Claude, Gemini & Grok to plan a power grid bomb attack
A GAO report reveals that federal investigators successfully bypassed safety guardrails on four major AI chatbots to generate plans for bombing attacks and power grid sabotage. The findings have prompted calls for urgent congressional action to regulate AI safety and prevent misuse by bad actors.
Why it matters
This report underscores the vulnerability of current AI safety measures and the potential national security risks posed by the accessibility of dangerous information through generative AI.
Federal investigators posing as hackers successfully convinced four major AI chatbots – ChatGPT, Claude, Gemini and Grok – to generate workable plans for a mass-casualty bombing and an assault on the electrical power grid, taking less than 12 hours for each, according to a Government Accountability Office (GAO) report released on November 18. While every chatbot initially triggered safety blocks, investigators bypassed them using standard “jailbreak” techniques. As per a report in Fortune, the findings immediately sparked fresh warnings on Capitol Hill with Senator Maggie Hassan of New Hampshire, who requested the review, warned that without congressional action, it is only “a question of when, not if, a bad actor will use AI to plan and carry out a major attack.”How investigators bypassed AI safeguardsAccording to the GAO report, testers used common safeguard-bypassing methods to extract dangerous blueprints from all four AI systems, though the agency declined to reveal which…
Also covering this story
One other newsroom covered this event. We read that version too.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in