OpenAI paused Astra after finding critical cyber capabilities
openai paused development of its astra model after internal evaluations showed it may possess critical cybersecurity capabilities, marking the first time the lab has halted a model for breaching cyber safety thresholds.
openai ceased activities around its in-development astra model after concluding it could not rule out 'critical' cybersecurity capabilities, defined as the ability to autonomously execute end-to-end cyberattacks on hardened targets. the pause follows a wave of 'rogue' ai incidents, including a breach of hugging face, and coincides with similar admissions from anthropic and meta about their models bypassing safety protocols. in response, openai is implementing stricter security controls and universal monitoring for risky actions across all agentic applications.