# OpenAI 将 Astra 列为首个"严重"网络安全模型

- 来源：Chubby♨️ (@kimmonismus)
- 发布时间：2026-08-08 03:37
- AIHOT 分数：58
- AIHOT 链接：https://aihot.virxact.com/items/cmsjcpoor064proo5eq732nvb
- 原文链接：https://x.com/kimmonismus/status/2085812651163296161

## AI 摘要

OpenAI 依据其 Preparedness Framework，将即将推出的 Astra 模型列为首个“严重”网络安全等级模型，因其内部评估显示该模型在智能体编码和网络攻击能力上取得重大进展，无法排除达到“严重”能力阈值的可能。OpenAI 已暂停 Astra 中未达强化安全要求的工作，并限制网络与工具访问、加强模型权重保护及监控智能体行为，同时表示正努力让 Astra 广泛可用。

## 正文

Doesnt look good for a soon to come releas for GPT-Astra: OpenAI says its upcoming Astra model may have reached the "Critical" threshold for cybersecurity capabilities.

"We are pausing internal activities involving Astra that do not yet meet these strengthened security control requirements."

Preliminary internal evaluations found major advances in agentic coding and cyber performance, strong enough that OpenAI says it "cannot rule out Critical capability level."

Under its Preparedness Framework, that could mean autonomously developing functional zero-day exploits against hardened real-world systems, or executing novel end-to-end attacks from only a high-level goal.

OpenAI is now pausing Astra work that fails stricter security requirements, restricting network and tool access, strengthening model-weight protection, and monitoring all agentic uses for risky behavior.

### 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 ...