Tensorwire
Models & releases · first seen 17 Sep, updated 17 Sep

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

1 outlet GPT & ChatGPT

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 ex…

Summary from InfoQ AI.

Coverage 1 article · 1 outlet

  1. InfoQ AI
    GPT-6 Astra Is the First Model OpenAI Classifies as Critical for Cybersecurity