Waymo says it is using DeepMind's Genie 3 to create realistic digital worlds for its autonomous driving technology to train on edge-case scenarios
Alphabet Inc.'s Waymo said it is using DeepMind's Genie 3 AI model to create realistic, digital worlds for its autonomous driving technology to train on edge-case scenarios.
The move follows Genie 3's release as a prompt-driven 3D-world model, giving Waymo a new way to produce training environments for unusual driving situations rather than relying only on existing simulations.
First-order effects
Waymo can incorporate Genie 3-generated digital worlds into training for edge-case scenarios, adding a generative source of simulated driving environments.
DeepMind gains a concrete internal deployment for Genie 3 in a safety-critical Alphabet business, linking the model to an operational autonomy workflow.
Second-order effects
Autonomous-driving developers face added pressure to improve the breadth and realism of simulated edge cases, where real-world collection is limited or costly.
Waymo's simulation pipeline becomes more tightly coupled to Alphabet's model-development capabilities, potentially reducing reliance on separately built scenario-authoring tools if the generated worlds prove useful.
Third-order effects
If generative world models become reliable training inputs, simulation may shift from manually designed test libraries toward continuously generated scenario coverage, making model quality and validation processes more central competitive assets.
The deployment points to a broader advantage for vertically connected AI groups: foundation-model research can be tested inside demanding product systems, though safety validation—not world-generation volume alone—will determine its value.
The trend: Generative world models are moving from general AI demonstrations into industrial simulation workflows where rare, high-consequence scenarios are difficult to capture directly.
We're excited to introduce the Waymo World Model—a frontier generative mode for large-scale, hyper-realistic autonomous driving simulation built on @GoogleDeepMind's Genie 3. By simulating the “impossible”, we proactively prepare the Waymo Driver for some of the most rare and [im…
WOW this is so incredibly cool. World models are helping self-driving cars simulate long-tail scenarios, which is crucial for robust autonomous systems. As powerful models like Genie 3 continue to advance, I'd expect post-training and adaptation to different hardware stacks
We've been working with our friends at Waymo for quite some time to bring world models to this critical domain. Reliably simulating rare, safety-critical OOD scenarios is one of the first viable applications of world models in the real world. We've demonstrated this just
I thought Genie 3 was cool, but not yet useful. Just a week later and now we get to see it's real world potential! @Waymo released their first world model built on top of @GoogleDeepMind 's Genie 3! The model can take real dashcam footage and expand it into interactive [video]
Genie 3 🤝 @Waymo The Waymo World Model generates photorealistic, interactive environments to train autonomous vehicles. This helps the cars navigate rare, unpredictable events before encountering them in reality. 🧵 [image]
Simulation has always been a critical component of Waymo's AI ecosystem and one of the 3 key pillars of our approach to demonstrably safe AI in the physical world. The Waymo World Model is a high-fidelity, controllable environment helping the Waymo Driver master the long tail.
This shit is so cool, I chatted with some NVIDIA folks at GTC years ago who were using a game engine to generate synthetic driving data with photogrammetry scenes. waymo.com/blog/2026/02...