Gergely Orosz：安全认证在 AI 智能体时代几乎无用
精选理由
Gergely Orosz 说安全认证防不住智能体时代的新威胁，他建议实时监控加智能体分析，运维和安全的人可以看看思路。
Gergely Orosz 在 X 上发帖称，传统安全认证在 AI 智能体带来的新型威胁面前价值很低。他提出应实时监控各项安全指标，用智能体持续分析实时数据。他还建议对延迟异常升高、异常系统访问等迹象保持偏执式的警惕，而不是依赖静态认证。
原文 · Gergely Orosz
These security certifications are less than useless in this new AI agent world of security threats.
What’s the certification checking that you’re obsessed with monitoring realtime; run agents analyzing all your realtime metrics; and your posture is “paranoid” on things like latency increases if services, attempts to access systems that have no business of accessing etc?
