X · Anthropic·· 6 天前AI 评分20
Anthropic 如何降低针对 Claude 的知识蒸馏攻击有效性
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
AI 导读
Anthropic 称过去几个月在降低针对 Claude 的知识蒸馏攻击有效性方面取得显著进展，并发布文章说明具体做法。原文未披露所用技术、模型版本或效果数据。
博主
Anthropic@AnthropicAI
粉丝 182万
认证：X 认证的官方组织
We're an AI safety and research company that builds reliable, interpretable, and steerable AI systems. Talk to our AI assistant @claudeai on https://t.co/FhDI3KQh0n.
互动数据
- 浏览
- 265万
- 点赞
- 6567
- 评论
- 844
- 分享
- 616
- 收藏
- 2392
数字来自平台，为最近一次抓取时的数据。
来源：X · Anthropic · x.com