Model Releases

OpenAI releases GPT-6 Astra and safety overview, saying its cybersecurity capability reaches Critical level in Preparedness Framework

Original title:Safety overview: GPT-6 Astra

AI summary

OpenAI released GPT-6 Astra, calling it its most capable deployed model and the first to reach the Critical cybersecurity capability level under its Preparedness Framework, able to discover unknown security vulnerabilities and develop exploits without step-by-step human guidance.

Key Takeaways

  • OpenAI released GPT-6 Astra
  • calling it its most capable deployed model and the first to reach the Critical cybersecurity…
  • able to discover unknown security vulnerabilities and develop exploits without step-by-step human…

Quick Facts

Published
Updated
Source
OpenAI:官网动态(RSS · 排除企业/客户案例)
Category
Model Releases
AI score
81
Read the original Read the full article at the original source
Why it matters

OpenAI 官方发布的安全评估,给出模型在网络安全能力、对齐和可监测性上的具体发现,读者可借此了解前沿模型安全实践的最新变化。

Related entities

Source & copyright

This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.

Original article · AIHOT entry

How to Cite

When citing this article, keep the title, date, and permalink, and credit Orange News as the source.

Orange News: OpenAI releases GPT-6 Astra and safety overview, saying its cybersecurity capability reaches Critical level in Preparedness Framework. September 3, 2026. https://new.nat6.net/en/news/cmtm02uu60t2arow5vd3nq4gi/

View all →