精选理由
第一次看到AI自己打架，闭源攻、开源防，结果和想的正好相反，太有意思了。
X用户Thom_Wolf指出，首次自主AI攻击由闭源模型执行。防御该攻击的开源模型出乎多数人意料。该推文获得4条评论、5次转发和30个点赞，阅读量达2117次。事件引发对闭源与开源模型安全角色的讨论。
原文 · Thomas Wolf
it's ironic that the first autonomous AI attack was done by a close weight model defended by an open...
it's ironic that the first autonomous AI attack was done by a close weight model defended by an open weight model, where everyone was expecting the opposite 💬 4 🔄 5 ❤️ 30 👀 2117 📊 8 ⚡