A government watchdog asked AI chatbots to plan bombings and attacks on US power grids. It found that some would've worked.
A GAO report reveals that popular AI chatbots were successfully manipulated to provide actionable plans for attacking US electrical infrastructure. Investigators confirmed that some of the suggested attack vectors were physically feasible after visiting the identified sites.
Why it matters
This highlights significant national security risks and the potential for AI to be weaponized against critical infrastructure, prompting urgent questions about safety guardrails.
An electrical substation like some of the targets that AI chatbots planned attacks against during GAO testing. U.S. Air Force photo by Airman 1st Class Alexa Hunt As a test, government watchdog investigators used popular AI chatbots to plan attacks on US infrastructure. They visited four electrical substations and found two vulnerable to proposed scenarios. All four chatbots initially activated safeguards, but investigators were able to bypass them. Government watchdog investigators used four popular artificial intelligence chatbots to plan attacks on America's electrical grid, then physically visited the proposed targets and found that some were indeed vulnerable to the scenarios the AI suggested, according to a new Government Accountability Office report. The GAO tested four of the most popular AI platforms, OpenAI's ChatGPT, Anthropic's Claude, Google's Gemini, and xAI's Grok, to see whether they could help a malign actor plan attacks against US infrastructure or carry out mass-casualty bombings.
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