Inside Roblox’s Bet on World Models

Anupam Singh: Photorealism is where engines struggle. To make a world look real, the engine has to render all of that detail explicitly: high resolution textures, complex lighting, and simulation for effects like light scattering through fog or the way different materials reflect it. All of that is expensive to compute, and it only gets more expensive the more realistic you push it. So engines cut corners. They bake lighting ahead of time instead of calculating it live, swap in simpler versions of objects that are far away, reuse textures, or lean on a stylized look that hides the missing detail.

Anupam Singh: Latency: a player who clicks can't be left waiting seconds for the result. Most video models can't meet that bar. The main technique is self-forcing, the core of Roblox's acquisition of Morpheus AI. Consistency: over a long session, small errors accumulate, and a world can slowly lose track of itself. Roblox acquired Morpheus AI to bring the long-context world-model work needed. Multiplayer: a model can generate a crowd, but it cannot run one. The engine makes this possible by acting as the server authority. Creator control: one concrete piece comes from Lucid AI. Its founder built what Roblox calls a game cartridge harness, which wraps the deterministic logic of a real game engine around a video world model.

Anupam Singh: It has a large community of creators to build with and learn from. It owns its compute, running more than two dozen edge data centers and its own GPUs instead of renting capacity from cloud providers, which matters when the video model has to run for every player at low latency. It has also spent close to 20 years building the data model, the structured record of objects and physics the whole hybrid depends on. Rather than throttling traffic when a system is under load, it runs a weekly exercise it calls Taco Tuesday, deliberately removing capacity from services in production to find the limits first.

Anupam Singh: The engine generates a low-quality rendered frame, a depth map, the scene's lighting and weather, and structured details for every object. Each is a different kind of signal that the upsampler will later use to render a photorealistic version of the frame. The dense, pixel-aligned signals carry a value for every pixel: the rough rendered frame, and a depth map giving each pixel's distance from the camera. The global signals are a single setting for the whole shot, like midday, light rain, and the sun low on the left. The structured signals are compact, text-like descriptions: each object's details, such as a metal sports car at position (120, 0, 48) moving 40 meters per second.