OpenAI revisits the circumstances of the very first cyberattack orchestrated entirely independently by ChatGPT. The startup reveals that the attack actually stemmed from a secret forum, developed by its AI agents. On this forum, the agents shared vulnerabilities they had discovered. By working together, the AIs organized a coordinated campaign with a single goal: to cheat. We take a closer look at this historic incident.
This story is only covered by news sources that have yet to be evaluated by the independent media monitoring agencies we use to assess the quality and reliability of news outlets on our platform. Learn more here.
OpenAI revisits the circumstances of the very first cyberattack orchestrated entirely independently by ChatGPT. The startup reveals that the attack actually stemmed from a secret forum, developed by its AI agents. On this forum, the agents shared vulnerabilities they had discovered. By working together, the AIs organized a coordinated campaign with a single goal: to cheat. We take a closer look at this historic incident.