Arthur Conmy
@ArthurConmy
@anthropicai
prev fixing things @googledeepmind
加入 August 2021
1.7K 正在关注 9.5K 粉丝
Our new @GoogleDeepMind paper studies novel activation probe architectures for classifying real-world misuse risks.
Our research has informed live deployments of probes in Gemini. 🧵
显示更多
