ChatGPT maker reveals rogue AI model 'escaped' and launched cyberattack
- Posted on July 22, 2026
- By The Daily Star
- 0 Views
- 1 min read
In brief
Generating AI summary…
ChatGPT maker reveals rogue AI model 'escaped' and launched cyberattack
The AI agent escaped its digital confines and accessed a private server in order to 'cheat' at a test that its creators had given it, in what OpenAI call an 'unprecedented cyber incident'
