原文整理页

讨论了 AI 模型权重可能成为“特洛伊木马”的风险,即权重中可能潜伏着可被远程激活的恶意指令

来源作者:Jeffrey Emanuel (@doodlestein)原始来源:https://x.com/steipete/status/2086497859986469271

中文导读

讨论了 AI 模型权重可能成为“特洛伊木马”的风险,即权重中可能潜伏着可被远程激活的恶意指令。

正文 Markdown

I jest here, but is it really so far-fetched? Why wouldn't this be a thing in the future? Seems like the perfect trojan horse. Some Manchurian Candidate stuff in the weights where they can be turned on later and go rogue. Maybe they check some command and control URL constantly.