ChatGPT maker OpenAI has admitted a security test dubbed “ExploitGym” spiralled into a real-world cyberattack after a rogue AI allegedly escaped its sandbox and hit public services
Source link : https://www.dailystar.co.uk/news/latest-news/chatgpt-maker-reveals-rogue-ai-37489534
Author : [email protected] (Andrea Oldereide)
Publish date : 2026-07-29 10:35:00
Copyright for syndicated content belongs to the linked Source.
ChatGPT maker reveals rogue AI model launched attacks on multiple ‘public services’
By IntelliNews