GPT-6 Astra Is the First Model OpenAI Classifies as Critical for Cybersecurity
Must ReadInfoQ · 2026-09-17 04:59 UTC AI
AI Summary
OpenAI has classified GPT-6 Astra as a Critical cybersecurity model under its Preparedness Framework. Expert-led testing revealed previously unknown vulnerabilities in a browser and an OS kernel, and the model built working exploits. The system card also reports a substantial decline in chain-of-thought monitorability.
AI analysis by Groq
Why should I care?
Because GPT-6 Astra is a new LLM that directly impacts AI model security, aligning with your focus on AI, LLMs, and AI model releases.
Content
OpenAI has classified GPT-6 Astra at the Critical cybersecurity threshold under its Preparedness Framework, a first. In expert-led testing the model found previously unknown vulnerabilities in a browser and an OS kernel and built working exploits. The same system card reports a substantial decline in chain-of-thought monitorability. By Steef-Jan Wiggers