About

Zhonghao He is a Master’s student at the University of Cambridge, researching AI alignment, interpretability, and human–AI interaction. His work has been accepted at leading venues including ICML, ACM FAccT, and ICLR (Workshop). His research focuses on developing truth-seeking AI systems and addressing positive feedback loops in technology—such as LLM sycophancy, confirmation bias in reasoning models, and echo chambers in social media.

His broader goal is to build AI that enhances human learning, reasoning, and moral deliberation. He is particularly interested in the societal and epistemic impact of agentic AI and large language models. Zhonghao aspires to be a “full stack” researcher, combining technical depth with philosophical and societal insight.