English
← Back to timeline

GPT-6 Astra Is Classified Critical for Cyber Capability

Era: The LLM Era · 2020s–Present

On September 3, 2026 OpenAI published a system card placing GPT-6 Astra at the Critical threshold for cyber capability under the company’s own Preparedness Framework, the first OpenAI model at that level. The card describes a model that can find previously unknown security flaws and develop ways to exploit them across many well-protected systems without a person guiding each step, and the sensitive capabilities are gated behind a trusted-access programme. The classification is OpenAI’s assessment of its own model against its own framework, and the card does not use the words AGI or general intelligence.

OpenAI

Status
Verified
Content type
industry-claim
Sources reviewed
Organizations
OpenAI

Sources and support

  1. GPT-6 Astra System Card

    OpenAI · Source type: primary-announcement

    OpenAI’s own system card states that the model meets their Critical threshold for cyber capability, the first OpenAI model placed at that level under their Preparedness Framework, and does not use the words AGI or general intelligence.

    Published: ·Accessed: