OpenAI评估Astra网络安全能力

OpenAI公布Astra在关键网络安全能力方面的初步评估结果，并披露针对潜在风险强化安全防护与控制措施的计划。该进展聚焦前沿模型在网络安全领域的能力边界和滥用防范。

事件进展（3 篇报道）

1. 2026-08-07 23:20
   OpenAI Blog Responding to the next frontier of critical cyber capabilities
2. 2026-08-08 02:40
   The Verge OpenAI puts the brakes on a new model because it’s supposedly too powerful
3. 2026-08-08 06:48
   TechCrunch OpenAI says it slowed Astra model development over security concerns

← 返回首页