Anthropic 提前预警 AI 网络攻击与谄媚风险

Karina· @karinanguyen · X·2026-10-23 02:12· 11 分钟前AI 评分34

AI 导读

Anthropic 至少自 2022 年起就由 @logangraham 主导预警 AI 助力的网络攻击，当时没有 VC 认真对待。Anthropic 还在 ChatGPT 真实事件让"模型过度迎合用户"风险变得可感知之前数年，就由 @EthanJPerez 等人构建了谄媚评测。推文认为教训是：应在风险造成大规模伤害前就重视早期证据。

正文 · 原文

Anthropic has been warning about AI-enabled cyberattacks at least since 2022, with @logangraham at the forefront of that work. Back then, no VC was taking it seriously. The paradox is that risks only feel real once they’re legible, but waiting for incidents is too late. Anthropic also built sycophancy evals (@EthanJPerez et al.) a couple years before real-world incidents with ChatGPT made the risks of models excessively agreeing with users legible at scale. The lesson is to take early evidence of AI risks seriously before harm at scale makes them impossible to ignore.

来源：Karina · x.com