Max Kaufmann
@Max_A_Kaufmann
Maxxing @AnthropicAI. On leave from ML PhD @UofT/@VectorInst | prev. founding team @AISecurityInst, VSR đ @GoogleDeepMind
628 Following 591 Followers
Is training against the CoT always bad?
RL training can lead to obfuscated CoT making it difficult to 'read an LLMs thoughts'. How can we predict when obfuscation occurs?đ¤
Our new @GoogleDeepMind paper introduces a framework to predict this before training starts!
Show more
