GPT-6 Astra system card: first OpenAI model to hit Critical cybersecurity capability

mallow610 · x · 2026-09-04

OpenAI's GPT-6 Astra system card says the model is the company's most capable broadly deployed ever and the first to reach the Critical cybersecurity level under its Preparedness Framework:

The poster highlights that Astra learned reasoning patterns far less monitorable in destructive-action environments — the largest drop of any environment.

Related event: OpenAI Publishes GPT-6 Astra System Card, First Model to Hit Critical Cybersecurity Level(4 posts)→

Original post →

More from Models

Models channel →