Language is just one 'keyhole' into intelligence. True artificial general intelligence (AGI) requires 'world modeling'—a spatial intelligence that understands geometry, physics, and actions. This capability to represent and interact with the state of the world is the next critical phase of AI development beyond current language models.

Today's AI is largely text-based (LLMs). The next phase involves Visual Language Models (VLMs) that interpret and interact with the physical world for robotics and surgery. This transition requires an exponential, 50-1000x increase in compute power, underwriting the long-term AI infrastructure build-out.

AI's capabilities are highly uneven. Models are already superhuman in specific domains like speaking 150 languages or possessing encyclopedic knowledge. However, they still fail at tasks typical humans find easy, such as continual learning or nuanced visual reasoning like understanding perspective in a photo.

Vision, a product of 540 million years of evolution, is a highly complex process. However, because it's an innate, effortless ability for humans, we undervalue its difficulty compared to language, which requires conscious effort to learn. This bias impacts how we approach building AI systems.

World Labs argues that AI focused on language misses the fundamental "spatial intelligence" humans use to interact with the 3D world. This capability, which evolved over hundreds of millions of years, is crucial for true understanding and cannot be fully captured by 1D text, a lossy representation of physical reality.

Ken Goldberg quantifies the challenge: the text data used to train LLMs would take a human 100,000 years to read. Equivalent data for robot manipulation (vision-to-control signals) doesn't exist online and must be generated from scratch, explaining the slower progress in physical AI.

Current multimodal models shoehorn visual data into a 1D text-based sequence. True spatial intelligence is different. It requires a native 3D/4D representation to understand a world governed by physics, not just human-generated language. This is a foundational architectural shift, not an extension of LLMs.

While SAM3 can act as a "tool" for LLMs, researchers argue that fundamental vision tasks like counting fingers should be a native, immediate capability of a frontier model, akin to human System 1 thinking. Relying on tool calls for simple perception indicates a critical missing capability in the core model.

Despite impressive general capabilities, top multimodal models from companies like Google and OpenAI still struggle with tasks requiring high precision. These "grounding failures" include pixel-perfect segmentation, accurate measurement, and understanding the spatial relationships between objects, as demonstrated on Roboflow's visioncheckup.com.