Google DeepMind has revealed Genie 3, its latest foundation world model that can be used to train general-purpose AI agents, a capability that the AI lab says makes for a crucial stepping stone on the path to “artificial general intelligence,” or human-like intelligence. Still in research preview and not publicly available, Genie 3 builds on both its predecessor Genie 2 and DeepMind’s latest video generation model Veo 3. Perhaps most importantly, Genie 3’s simulations stay physically consistent over time because the model can remember what it previously generated — a capability that DeepMind says its researchers didn’t explicitly program into the model. While Genie 3 has implications for educational experiences, gaming or prototyping creative concepts, its real unlock will manifest in training agents for general-purpose tasks, which he said is essential to reaching AGI. “We think world models are key on the path to AGI, specifically for embodied agents, where simulating real world scenarios is particularly challenging,” Jack Parker-Holder, a research scientist on DeepMind’s open-endedness team, said. Genie 3 is supposedly designed to solve that bottleneck. Like Veo, it doesn’t rely on a hard-coded physics engine; instead, DeepMind says, the model teaches itself how the world works by remembering what it has generated and reasoning over long time horizons. That memory, the company says, lends to consistency in Genie 3’s simulated worlds, which in turn allows it to develop a grasp of physics, similar to how humans understand that a glass teetering on the edge of a table is about to fall, or that they should duck to avoid a falling object. Notably, DeepMind says the model also has the potential to push AI agents to their limits — forcing them to learn from their own experience, similar to how humans learn in the real world.