OpenAI designates Astra as its first 'Critical' cybersecurity model

OpenAI 将 Astra 列为首个"关键"网络安全模型

OpenAI evaluated its upcoming model Astra under its Preparedness Framework and labeled it 'Critical' for cybersecurity risk—the highest tier. The company says it planned for this scenario, will add extra safeguards, and aims to put Astra's advanced cyber capabilities in defenders' hands. The post doesn't disclose model specs, release timeline, or the quantitative thresholds for the Critical designation.

Why it matters: OpenAI's first self-assessment labeling an unreleased model 'Critical' on cybersecurity is a signal in itself. But the post doesn't disclose parameters, release timeline, or the quantitative threshold for 'Critical,' which caps the score below 85.