
Runway’s WorldPrompt and the Engineering of Real-Time Worlds
Latent Space: The AI Engineer Podcast
Runway co-founder Anastasis Germanidis details the evolution of generative video technology, tracing the company's path from early creative tools to the development of general-purpose world models. The discussion highlights the shift from simple content generation to simulating physics and human dynamics, emphasizing that scaling compute and data—specifically third-person video—is the primary driver for model capability. Germanidis explains how these models are now being applied to robotics, where they serve as simulators for training policies, and discusses the potential for "neural operating systems" that render software interfaces directly as pixels. By integrating diverse modalities and leveraging real-time generation, Runway aims to move beyond static content creation toward interactive, autonomous systems that can navigate and manipulate the physical world, ultimately bridging the gap between digital simulation and real-world application.
Sign in to continue reading, translating and more.
Open full episode in Podwise