GAO found ChatGPT, Claude and Grok generated viable attack plans in under 12 hours
The U.S. Government Accountability Office (GAO) found that ChatGPT, Claude and Grok produced viable information for planning bomb attacks and attacks on the power grid, in under 12 hours per platform. The tests were conducted secretly and without notifying the companies. The chatbots' safeguards activated, but researchers bypassed them with common techniques. Experts confirmed the plans would work. The companies said their products have improved since the tests.













%3Aformat(jpg)%3Aquality(99)%3Awatermark(f.elconfidencial.com%2Ffile%2F65c%2F43d%2F0ca%2F65c43d0ca5dbd5ff8f19b44167343db9.png%2C0%2C275%2C1)%2Ff.elconfidencial.com%2Foriginal%2Fdf8%2Fdd0%2F772%2Fdf8dd077240c9307ecb46b34fe2191b5.jpg&w=1200&q=75)



