aiqbench takeAI Safety

OpenAI has officially designated GPT-6 Astra as "Critical" within its Preparedness Framework due to its demonstrated ability to autonomously discover zero-day vulnerabilities and construct functional exploits for hardened browsers and OS kernels. This milestone highlights a significant shift in AI capabilities, where models can now independently identify previously unknown security flaws and adapt them into working attack chains without human intervention. The classification underscores the emerging dual-use nature of advanced LLMs, presenting both a powerful tool for defensive red-teaming and a potential vector for autonomous cyberattacks if misused.

Sources coveringInfoQ, Latent Space, arXiv

What this isA model's reading of the article and related coverage, written for aiqbench. Not the publisher's words.

GPT-6 Astra is the First Model OpenAI Classifies as Critical for Cybersecurity

InfoQSeptember 17, 20265 min read

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

OpenAI has classified GPT-6 Astra at the Critical level for cybersecurity capability under its Preparedness Framework, the first model to reach that threshold. Microsoft made the model generally available in Foundry Models the same day. The distribution is broader than a single cloud. OpenAI's own announcement listed availability through ChatGPT tiers, the API, and AWS, without naming Azure, which drew comment on Hacker News. One commenter drew the distinction that matters: being hosted on Azure is different from being provided by Azure, where the latter is…

Excerpt shown under the publisher's RSS terms · 86 words · full text and figures are on the publisher's site

Read at InfoQ ↗Ask about this article