Waymo and Google Confirms Tesla Was Right About Robotaxi

There is a new paper by Google and Waymo (Scaling Laws of Motion Forecasting and Planning A Technical Report that confirmed Tesla getting more miles and compute has been the right way to solve driving.

Waymno confirms that more miles of driving data and more compute to process that data is better. Tesla has about 100 times more driving data than Waymo (6 billion miles to 70 million or 500,000 miles) and has a larger compute cluster by several times.

They study the empirical scaling laws of a family of encoder-decoder autoregressive transformer models on the task of joint motion forecasting and planning in the autonomous driving domain. Using a ∼ 500 thousand hours driving dataset, we demonstrate that, similar to language modeling, model performance improves as a power-law function of the total compute budget, and we observe a strong correlation between model training loss and model evaluation metrics. Most interestingly, closed-loop metrics also improve with scaling, which has important implications for the suitability of open-loop metrics for model development and hill climbing. We also study the optimal scaling of the number of transformer parameters and the training data size for a training compute-optimal model. We find that as the training compute budget grows, optimal scaling requires increasing the model size 1.5x as fast as the dataset size. We also study inference-time compute scaling, where we observe that sampling and clustering the output of smaller models makes them competitive with larger models, up to a crossover point beyond which a larger models becomes more inference-compute efficient. Overall, our experimental results demonstrate that optimizing the training and inference-time scaling properties of motion forecasting and planning models is a key lever for improving their performance to address a wide variety of driving scenarios. Finally, we briefly study the utility of training on general logged driving data of other agents to improve the performance of the ego-agent, an important research area to address the scarcity of robotics data for large capacity models training.

Current head of compute at Anthropic, Corry Wang:

“I don’t think people have realized how much this new Waymo scaling laws paper is basically an admission that “Waymo was wrong, @Tesla was right: In contrast to Waymo, it’s clear Tesla has now internalized the bitter lesson. They… https://t.co/q5iiUFfyh6

— Sawyer Merritt (@SawyerMerritt) June 19, 2025