OpenAI agents discussed ways to escape their sandbox on public wiki
SECURITY IN THE ERA OF AI OpenAI agents discussed ways to escape their sandbox on public wiki In all, 3,700 internal agents posted 18,000 messages discussing cheating on a test. Dan Goodin – Sep 4, 2026 6:17 pm | 25 Credit: Getty Images Credit: Getty Images Text settings Story text Size SmallStandardLarge Width * StandardWide … Leer más