Goodfire Research·· 2 小時前AI 評分8
神經網絡已經是乾淨的
Neural Networks Are Already Clean
AI 導讀
標題主張神經網絡已經是乾淨的，但所附正文沒有解釋或佐證這項主張。頁面另列出有關 Kimi K3 生產級網絡安全監察器、以蛋白質嵌入向量改善 AI 智能體生物安全監察，以及大規模捕捉模型 reward hacking 的內容，並介紹 Silico 的可解釋性 Agent。
正文
Research
Training and Deploying Production Cyber Monitors on Kimi K3
October 8, 2026
Better biosecurity monitors for AI agents via protein embeddings
October 1, 2026
Models know when they’re reward hacking — and we can catch them at scale
September 17, 2026
Silico is your interpretability agent.
Explain, debug, and precisely control model behavior with state-of-the-art interpretability methods and infrastructure
來源：Goodfire Research · goodfire.com