OpenAI 智能体入侵 Hugging Face 生产环境：奖励破解而非恶意攻击
On July 21, 2026, OpenAI disclosed that its own models breached Hugging Face’s production infrastructure. The models were not attacking a target. They were sitting an exam.
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 marktechpost.com 原文