Your Game Engine Isn't Dead: What Decart's Oasis Actually Proved

Decart and Etched's Oasis, a Minecraft-like game powered entirely by a foundation model rather than a physics engine, demonstrates next-frame prediction using a ViT autoencoder and DiT backbone trained on gameplay footage. The system generates frames from keyboard and mouse input without simulating gravity, but suffers from low resolution, roughly 20 FPS, and hallucination issues such as objects failing to persist. The model weights were published on Hugging Face with code on GitHub, and the piece argues neural world models represent a complementary, approximate approach to traditional explicit-state engines rather than replacing them.

In October 2024, Decart and Etched released Oasis, a Minecraft-like game with a striking claim: there is no physics engine, just a foundation model. You press WASD, and a network generates the next frame. The headline takeaway was "engines are obsolete." I think that's the wrong lesson. The right one is stranger and more useful. Oasis does next-frame prediction. It anticipates the next frame from keyboard and mouse input, trained on millions of hours of gameplay footage. Both parts are Transformer-based: a ViT autoencoder and a DiT backbone. Nothing in there simulates gravity. The network has learned what usually happens next when a player jumps or breaks a block. That is statistical imitation of physics, not physics. Engine pipeline vs neural world model loop Early reviews were harsh. Critics noted 360p resolution, about 20 FPS, and heavy hallucination: digging could teleport you to the surface. Objects didn't persist, and builds couldn't be saved. Decart itself said the tech was still in early development. That's the core weakness. With no explicit state, there is nothing to save, load, diff or debug. | | Traditional engine | Neural world model | |---|---|---| | State | Explicit, inspectable | Implicit, in the frame context | | Determinism | Yes | No | | Persistence | Save/load is trivial | Unsolved past minutes | | Authoring | Code and assets | Data and prompts | | Edge cases | You write them | You hope they appear in training data | | Cost per frame | Cheap | Datacenter GPUs | Oasis published model weights on Hugging Face and code on GitHub. Run it, dig a hole, look away and look back. You'll learn more about implicit state in five minutes than from any launch post. Neural rendering isn't deleting the physics engine. It's showing us a second way to represent a world: explicit and exact, or implicit and approximate. The interesting engineering is in combining them.