Goodfire Research·· 2026-10-08PicksAI score71
Goodfire trains and deploys probe-based cyber misuse monitors on Kimi K3 and GLM 5.3
Training and Deploying Production Cyber Monitors on Kimi K3
AI summary
3 and deployed them on a production inference stack, where a cheap probe filters turns and only suspicious exchanges reach an LLM judge. 5% benign-session interruption rate, costs $65 per million turns without judge reasoning and $185 with it, and adds no measurable throughput loss inside SGLang.
Why it matters
Goodfire shows a probe-plus-judge cascade can monitor agentic cyber misuse at roughly 50x lower cost with no measurable throughput loss, a concrete recipe for serving open models safely.
Source:Goodfire Research · goodfire.com