Xi Zhu

Forget complex architectures: the secret to self-improving LLM agents lies in teaching them how to *interpret* their past failures, not just remember them.

LLMs can mimic your style, but your friends can still tell it's not really you, especially when it comes to your opinions.

LLMs still can't convincingly mimic human personas, especially when it comes to syntactic style and memory, despite advancements in other areas.