Why your AI can read but can't watch (yet)

Everyone's talking about AI, but can it actually watch and understand video the way we do? Josemaria Soriano sits down with our co-founder and Head of World Models Mateusz Malinowski to break down Vision Language Models (VLMs): What they are, How they differ from chatbots and traditional computer vision, and Why the gap between "good enough" and "95% accurate" matters for real businesses, from sports broadcasting to public safety to Hollywood.