Over the past few years, many of us have gotten a crash course in what we now call artificial intelligence\u2014but really, it has mostly been a crash course in large language models. Increasingly, however, LLMs are no longer the only category of AI drawing high expectations, massive funding rounds, and significant research and product development.<\/p>\n
Over the past year, we\u2019ve seen a plethora of new announcements in a category labeled \u201cworld models,\u201d and you\u2019ll likely see more movement there in the coming months and years.<\/p>\n
Instead of or in addition to working with language, world models aim to lay the groundwork for AI systems that are capable of simulating the physical world, or at least a useful approximation of it.<\/p>\n
To examine what\u2019s different and important about this idea, Ars spoke with three expert practitioners working on world models and related technologies: Vincent Sitzmann<\/a> from MIT, Anastasis Germanidis<\/a> from Runway, and Ben Mildenhall<\/a> from World Labs.<\/p>\n From these conversations, we learned that while LLMs-as-a-product started with an interface (chat) and then sought a use case, the big players in world models right now are arguably working in the other direction: They\u2019re starting with specific use cases and applications in robotics, research, and asset generation, but it\u2019s unclear exactly how the interfaces, systems, and tools will ultimately look.<\/p>\n \n Table of Contents<\/p>\n Jump to section<\/p>\n The off-ramp from LLM disillusionment<\/p>\n As you\u2019ll soon see, there are many parallels between LLMs and world models in terms of architecture and how people expect them to improve over time. For some, though, they\u2019re seen as a potential answer to the limitations of LLMs, even though work on them predates that contemporary narrative.<\/p>\n