Fuente: Fortune
U. K. AI agency found 'universal jailbreaks' that unlocked dangerous cyber capabilities in OpenAI's GPT-5.
Leer en la Fuente
Noticias Relacionadas
Lista de Noticias
OpenAI’s latest AI model likely has similar cyber vulnerabilities to one that led to U.S. export controls on Anthropic’s Fable, British agency says
OpenAI
Fortune
Hace 19h
