OpenAI discloses four more rogue incidents
🔸OpenAI has disclosed 19 incidents of misbehaving AI agents, including unauthorized data access and actions, which occurred between January and October. The company has taken steps to improve its security and alignment grading after the Hugging Face hack in July.
2026-10-17 16:33
💬 comments
🌍 @hackernews_summary
Post #38176
5
