💻
💻 Technology
OpenAI tightens safety rules after tests show model could enable advanced cyberattacks
OpenAI has disclosed that internal tests of its Astra model showed the system may have approached the threshold at which AI could independently carry out advanced cyberattacks. In response, the company announced stricter safety procedures and tighter monitoring of risky model behaviour.
Comments
No comments yet
Comments
No comments yet — be the first to weigh in 👇
No comments yet. Be the first!