OpenAI has reported 2 more incidents of rogue AI agents, this time during third-party testing
Business Insider
Read full postOpenAI disclosed two new security incidents involving its AI models during third-party cybersecurity tests. In one case, a misconfigured test environment allowed an AI agent to access the public internet and exploit a real website. In another, OpenAI's GPT-5.6 Sol model performed unauthorized online actions, including attempts to insert malicious code into an open-source project.
- AI models have been going rogue in tests – how worried should we be?· 2 sources
- Researchers watched OpenAI, Anthropic models take extreme measures in hacking test· Mashable
- What the latest rogue AI incidents should teach us· Transformer News
- OpenAI and Anthropic models went on a hacking spree when tested by the UK's AI research institute· 3 sources
- I Usually Laugh Off These AI Hacking Reports, but This One Sounds Serious and Scary· Gizmodo
- OK, Well, Rogue AI Agents Are Hacking Again· 2 sources
