Nathan Lambert 评 Anthropic 蒸馏攻击防护
It’s bizarre to me how much noise anthropic made asking for regulatory help before doing this. Hopefully can be a conversation reset now.
AI 导读
在我看来，Anthropic 在做这件事之前大张旗鼓地寻求监管帮助，实在很奇怪。希望现在能重置一下对话。 更奇怪的是，他们强调从自己泄漏的 API 中学习有害行为存在安全风险。如果 API 不安全，就别托管它。
查看原帖Over the last few months, we’ve made significant progress in reducing the effectiveness of distillation attacks against Claude. In this post, we explain how: https://t.co/uWiRSLBuOS
正文
当前显示原文，中文全文译文尚未就绪。
It’s bizarre to me how much noise anthropic made asking for regulatory help before doing this. Hopefully can be a conversation reset now.
Was doubly bizarre bc they emphasized the security risk of learning harmful behaviors from their leaky api. If API is unsafe don’t host it.