Arthur Conmy
@ArthurConmy
@anthropicai
prev fixing things @googledeepmind
参加 August 2021
1.7K フォロー中 9.5K ファン
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. 🧵
もっと見る
