Safety overview: GPT-6 Astra

TL;DR - OpenAI says GPT-6 Astra is its most capable broadly deployed model and its first to reach the Critical cybersecurity capability level under the company’s Preparedness Framework.

• The announcement concerns a broadly deployed OpenAI model.
• Its cybersecurity capability is classified as Critical under OpenAI’s framework.
• The provided excerpt does not detail the evaluation methods, safeguards, or specific cyber capabilities behind that classification.