Jack Morris

In this engaging discussion, Jack Morris, a PhD grad student at Cornell Tech, unpacks the intricate relationship between information theory and large language models. He shares fascinating insights about the efficiency of data representation in AI, particularly in models like GPT-3. The conversation dives into the revolutionary concepts of embedding inversion and the implications for model alignment and security. Jack also explores the potential of emerging programming languages like Mojo, merging performance with innovation in AI research.