The Missing World Model: What Machines Know That Cameras Can't See

InnovationThe Missing World Model: What Machines Know That Cameras Can't SeeByBrandon Barbello,Forbes Councils Member.for Forbes Technology CouncilCOUNCIL POSTExpertise from Forbes Councils members, operated under license. Opinions expressed are those of the author. | Membership (fee-based)Jun 02, 2026, 07:15am EDTBrandon Barbello is Co-Founder & COO of Archetype AI, with 10+ years of product leadership across Fortune 500 and startups.​ gettyWorld models are having a moment. Fei-Fei Li's World Labs has raised over $1 billion. Yann LeCun has launched a new venture with comparable backing, and physical AI headlined NVIDIA GTC. The premise driving this new wave of interest is simple: The physical world is too messy, interconnected and unpredictable to navigate with traditional rules-based approaches.As someone who spent almost a decade at Google building on-device AI and multimodal sensing systems before founding Archetype AI, I've watched the world models conversation unfold with real excitement. But as it's taken flight, one critical piece has been missing from this conversation.​There's A Spectrum, And We're Only Looking At One EndWorld models can be thought of as existing on a spectrum. Both ends share the goal of understanding the physical world, but they take very different approaches to doing so.​At one end is simulation. World Labs generates purely virtual, fictional environments. NVIDIA's Cosmos and Omniverse simulate the real world with enough fidelity that robots and autonomous vehicles can be trained in synthetic environments before operating in the real one. Google DeepMind's Genie pushes further still, simulating not just visual scenes, but richer scenarios incorporating driving conditions, weather events, radar and LiDAR. That last step signals that the field understands vision alone isn't sufficient.​At the other end of the spectrum is runtime world modeling. This approach doesn't simulate the world...