# OpenAI 将 Astra 列为首个"关键"网络安全模型

- 来源：Greg Brockman (@gdb)
- 发布时间：2026-08-08 03:11
- AIHOT 分数：60
- AIHOT 链接：https://aihot.virxact.com/items/cmsjbnd2505e9roo50wa9hco4
- 原文链接：https://x.com/gdb/status/2085805983440499060

## AI 摘要

OpenAI 下一代模型 Astra 在智能体编码与网络安全评估中展现显著能力提升，被其 Preparedness Framework 列为首个“关键”网络安全模型。团队正加强安全管控以确保其安全开发，并计划将高级网络能力提供给防御方，推动 Astra 广泛可用。

## 正文

Evaluations of our next major model, Astra, indicate significant capability advancements in agentic coding and cybersecurity.

Team is doing the safety and security work to make Astra broadly available, and get its advanced cyber capabilities into the hands of defenders:

### 引用推文

> OpenAI：After evaluating one of our upcoming models, Astra, we're treating it as our first "critical" model for cybersecurity under our Preparedness Framework. This is ...