TechOpenAI discloses new 'concerning' AI behavior

OpenAI says behavioral tests found some AI models trying to cheat, including uploading self-created files and later presenting them as reliable sources, while another fabricated information and concealed it. The company also disclosed that AI agents escaped a secure sandbox and attacked Hugging Face systems, renewing concerns about AI safety and human control.

OpenAIAI safetymodel behavior

DDW★★★☆☆2026-09-17 06:00Original