Safety overview: GPT-6 Astra

OpenAI published a safety overview for its GPT-6 Astra model. The document describes GPT-6 Astra as the company's most capable broadly deployed model and highlights that it is the first to attain the Critical level of cybersecurity capability within OpenAI's Preparedness Framework.

Summary written by Kernelia from the original article by OpenAI News. The story and its rights belong to its author.