The interactive capability from Genie includes 3D simulations at 720p resolution, allowing Waymo's "driver" to practice edge-case scenarios in a virtual environment that maintains consistent physics and persistent memory.

This combination of broad world knowledge, fine-grained controllability, and multi-modal realism enhances Waymo’s ability to safely scale our service across more places and new driving environments.

Waymo says the model can create “hyper-realistic” simulated environments that train the AI on situations that are rarely (or never) encountered in real life—like snow on the Golden Gate Bridge.

Until recently, the autonomous driving industry relied entirely on training data collected from real cars and real situations. That means rare, potentially dangerous events are not well represented in training data. The Waymo World Model aims to address that by allowing engineers to create simulations with simple prompts and driving inputs.

 

That as Waymo continues to take on more investment capital, according to Yahoo Finance, which says the company recently closed a $16 billion funding round that pushed its valuation to an amazing $126 billion.

All that capital will used to expand fleet growth and operations as Waymo keeps growing its driverless vehicles in cities such as San Francisco, Los Angeles and Miami.

(See More Below)

 

“Alphabet's ability to generate accurate synthetic driving data through Genie 3 reduces the need for massive physical test fleets in every new city, potentially protecting margins during the capital-intensive scaling phase” Yahoo also reports.

While competitors remain reliant on vast amounts of real-world sensor data, Waymo's integration of high-resolution generative simulations marks a pivot toward a more software-centric, scalable rollout model, Waymo says.

By leveraging Genie’s immense world knowledge, it can simulate exceedingly rare events—from a tornado to a casual encounter with an elephant—that are almost impossible to capture at scale in reality. The model’s architecture offers high controllability, allowing our engineers to modify simulations with simple language prompts, driving inputs, and scene layouts. Notably, the Waymo World Model generates high-fidelity, multi-sensor outputs that include both camera and lidar data.

Waymo adds that this combination of broad world knowledge, fine-grained controllability, and multi-modal realism enhances Waymo’s ability to safely scale our service across more places and new driving environments.