OpenAI's GPT-6 Astra hits Critical cybersecurity level; system card adds 3 bio evals

alishbaimran_ · x · 2026-09-04

OpenAI has released the GPT-6 Astra system card. Astra is the most capable model OpenAI has broadly deployed and the first to reach the Critical cybersecurity threshold under its Preparedness Framework—able to find unknown vulnerabilities and develop new exploits across hardened systems without step-by-step human guidance.

Key points:

Contributing OpenAI researcher alishbaimran calls it a pivotal moment spanning capability measurement, monitorability, and safeguards.

Related event: GPT-6 Astra Launch: Capability Leap Marred by Benchmarking Dispute and Declining Monitorability(62 posts)→

Original post →

More from Models

Models channel →