Q&A with NYU professor Julian Togelius on his recent paper about LLMs' limitations in playing video games, why coding is a kind of well-designed game, and more (Matthew S. Smith/IEEE Spectrum)

Matthew S. Smith / IEEE Spectrum: Q&A with NYU professor Julian Togelius on his recent paper about LLMs' limitations in playing video games, why coding is a kind of well-designed game, and AI models code simple games, but struggle to play them - Large language models (LLMs) have improved so quickly …