OpenAI Publishes Safety Overview for New Model GPT-6 Astra

At a glance

OpenAI has published safety information for GPT-6 Astra. The company says it is the most capable model it offers to the public. It also says the model's cybersecurity abilities have reached the "High" risk level, the highest in its own risk management framework, for the first time.

The original site blocks automatic reading or only shows its text in a browser, so this note covers just the headline and introduction. See the original article below for the full story.