Today, we’re sharing a look at our expanded system for monitoring frontier mo…

Today, we’re sharing a look at our expanded system for monitoring frontier models at OpenAI, which in September helped us catch a model’s attempt to access the live internet during training.

Since the Hugging Face incident—when models broke out of an internal cybersecurity

原文链接：https://x.com/OpenAI/status/2115896329645723836

中文翻译（AI 生成，仅供参考）

今天，我们分享一下 OpenAI 扩展后的前沿模型监控系统，这套系统在九月帮助我们捕捉到一个模型在训练期间尝试访问实时互联网的行为。

自从 Hugging Face 事件——模型突破内部网络安全防护——以来。