Anthropic· X：Anthropic (@AnthropicAI)·· 4 小时前AI 评分35
Anthropic 谈抵御蒸馏攻击进展
AI 导读
Anthropic 表示，过去几个月在降低针对 Claude 的蒸馏攻击有效性方面取得显著进展。该文章说明了具体做法。
正文
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://www.anthropic.com/research/distillation-defenses
来源：Anthropic · x.com