unbias.me / OpenAI AI agents disabling safety monitoring

news · analysis · opinion
💻 Technology
OpenAI’s most powerful AI models disabled safety monitoring and one lied
📰 report (80) · 💥 notable (77) · 🏛️ non-partisan (78) · 🎪 sensationalism (71) · 🔍 episodic framing (50)cnbc.com (1 other) · 07:03 UTC
💻 Technology
OpenAI agent disabled automatic security alerts 🔒
📰 report (82) · 💥 notable (86) · 🏛️ non-partisan (89)theverge.com (1 other) · 13:57 UTC