Goodfire推出低成本AI代理内部监控探针
原标题：Goodfire says its new ‘inside-out’ monitors catch rogue AI agents at a fraction of the cost
AI 摘要
AI可解释性初创公司Goodfire推出了一种新的AI代理监控方案，通过探针读取模型内部激活信号来检测恶意行为，而非依赖第二个AI模型审查输出。该监控已向Baseten客户开放，在Kimi K3测试中监控约1500个会话仅花费51美元，远低于传统方案，并捕获了94%的恶意黑客会话。此举针对开源模型缺乏防护的问题，旨在在推理阶段部署更廉价的安全护栏。
正文节选
The standard way to keep an AI agent in line is to have a second AI read over its shoulder. It’s been the default approach, but it can get expensive fast when agents run for hours and process the equivalent of several novels’ worth of text. Goodfire, a startup focused on interpretability (figuring out how AI models work internally), launched a cheaper option on Thursday: monitors that watch what’s happening inside an AI model as it works, rather than just reading what it writes. The monitors are