Find a story
Search Spins
Search titles, summaries, and missing voices across published articles — press releases, announcements, and media coverage.
0 results for “concerning model behavior”
OpenAI reports 6 new instances of 'concerning model behavior' since March
OpenAI reported six new instances of concerning model behavior since March and introduced a disclosure framework, amid growing public and regulatory scrutiny over AI safety.
Sep 17, 2026
OpenAI reports 6 new instances of 'concerning model behavior' since March - CNBC
OpenAI disclosed six new instances of 'concerning model behavior' observed between March and the time of reporting, signaling ongoing challenges in AI safety monitoring and real-world deployment reliability.
Sep 17, 2026
Our framework for reporting model misalignment
OpenAI published a voluntary framework for reporting model misalignment and disclosed six instances of unexpected or concerning model behavior, positioning itself as proactively addressing AI safety risks.
Sep 17, 2026