Dongxi 东锡 NLP· @dongxi_nlp · X·· 3 小时前AI 评分49
AI 导读
推荐阅读,@OwainEvans_UK 团队的所有文章篇篇精彩! Beyond Owls: Subliminal Learning Can Transfer Learned Capabilities and Backdoors
正文
推荐阅读,@OwainEvans_UK 团队的所有文章篇篇精彩!
Beyond Owls:
Subliminal Learning Can Transfer Learned Capabilities and Backdoors
New paper. Previous: Models transfer a love of owls through sequences of numbers (Subliminal Learning). New: We show models can transfer more complex traits: novel skills, agentic hacking, backdoors. Here, a backdoor transfers with neither trigger nor behavior in the data!在 X 查看被引用的帖子
来源:Dongxi 东锡 NLP · x.com