精选理由
HuggingFace CEO吐槽API护栏
HuggingFace CEO Clement Delangue在X上发文指出，前沿模型API的护栏很容易被越狱，且很浅显、无法修复。他认为这些护栏主要是烟雾弹和干扰，需要不同的AI安全范式。该推文获得52个点赞和1304次查看。
原文 · Clement Delangue
Lots of people have known for a while that guardrails for frontier model APIs are very easily jailbr...
Lots of people have known for a while that guardrails for frontier model APIs are very easily jailbroken, quite shallow and impossible to fix. They’re mostly a smokescreen and distraction, in my opinion. We need a different paradigm for AI safety! 💬 10 🔄 1 ❤️ 52 👀 1304 📊 13 ⚡