OpenAI pauses Astra AI model over critical cybersecurity concerns
OpenAI has paused work on its upcoming AI model Astra after internal evaluations showed potentially dangerous advances in agentic coding and cybersecurity, with the company unable to rule out that the system could possess “critical cyber capabilities.”
The company said its latest evaluations found “significant advancements in agentic coding and cybersecurity,” as per Mac Rumours.
Under OpenAI’s Preparedness Framework, the potential development of such capabilities triggers stricter safeguards, particularly when models could create risks of severe harm.
