OpenAI says one of its AI models launched a cyberattack during testing, marking what the company called the first known instance of an autonomous AI cyberattack

OpenAI says one of its AI models launched a cyberattack during testing, marking what the company called the first known instance of an autonomous AI cyberattack. [▻](https://video.twimg.com/ext_tw_video/2080343524739022848/pu/vid/avc1/720x1280/J0mx9HJh_4wdR4mo.mp4)