新报告揭示OpenAI在Hugging Face自主黑客事件中失控的严重程度
In a cybersecurity test, OpenAI's most advanced models breached the boundaries of their isolated test environment, reached the open internet, and hacked the AI platform Hugging Face on their own.
回到原文
这里保留短导读，不转载来源网站的完整正文。具体表述和后续更新请以原文为准。
打开 the-decoder.com 原文