Arthur Conmy
@ArthurConmy
@anthropicai
prev fixing things @googledeepmind
1.7K Following 9.5K Followers
I'm joining Anthropic!
I'll start work on aligning upcoming models as they’re trained
Claude's capabilities are extraordinary. But like all models thus far, Claude isn’t aligned enough to safely delegate AGI development to
I can't think of a better place to work on this at
Show more
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. 🧵
Show more
