Import AI (Jack Clark)Dec 22, 2025, 1:31 PMJack Clarkimportant 75
Import AI 438：無聲的警報，為我們所有人閃爍（網路安全能力過剩與對話隱私）
Original: Import AI 438: Silent sirens, flashing for us all
In this issue of Import AI 438, Jack Clark examines two key issues concerning AI security and privacy: **1. You Are Your LLM History** As…
本期 Import AI 聚焦於兩個核心議題：首先是「你就是你的對話歷史」，研究指出使用者的 LLM 對話紀錄具有高度獨特性，足以像指紋一樣識別個人身分並洩露隱私；其次是「網路安全能力過剩（Cyber Capability Overhang）」，指出當前 AI 模型可能已具備強大的網路攻擊潛力，只是因缺乏適當的鷹架工具（Scaffolding）或提示而尚未顯現，這種潛在威脅如同無聲的警報，隨時可能被觸發。
In this issue of Import AI 438, Jack Clark examines two key issues concerning AI security and privacy:
Full summary
Free shows the 3-line summary; Pro unlocks the full deep summary (~300 words) so you never have to click through.
See Pro plans →Want the original English / full article?
Read on Import AI (Jack Clark) →Summaries are AI-generated; the original article is authoritative.