2026-05-19

AT is optimized for large-scale pre-training and it's nearly three times the raw computing power of our previous generation. We have taken a fundamentally different approach with our training infrastructure. With Jackson Pathways, our training is no longer constrained by the limits of a single massive data center. Instead, we can now seamlessly distribute training across multiple sites, scaling across more than one million TPUs globally. This gives us the ability to create the largest training cluster in the world. For model builders, this means training larger, more capable models in weeks rather than months. TPU-8i is designed for inference. We have dramatically improved speed at every step because if we learn anything in 27 years of working on Search, it's that latency matters. To give you a live sense of what the speed feels like, here's a prompt on an upcoming Flash model if it were running on 8i. I'll ask it to create a Chrome dino game, push submit. The response is generated in real time. As you watch, take a look at the tokens per second in the top right corner. The speed is pretty incredible, nearly 1,500 tokens per second. It almost took longer to write out the request, and the game is pretty fun too. In addition to speed, we are also thinking about scaling sustainably. Both chips are more energy efficient, delivering up to two times better performance per watt. TPUs have been hard at work training for I.O. this year. I'm told we have a behind-the-scenes look.