More than speed: Building a network for all of life’s biggest moments

The Game Day Difference

Game day. For millions of people, it's about the excitement, the big plays, and the drama unfolding on the field (or for most of us, on the screen). For our teams at GFiber, it's a real-world test of everything we've built. The traffic from major live events, like the September 5 NFL game in São Paulo, isn't like a normal day's usage. We anticipated this sudden surge and were ready.
This is where the GFiber difference comes in. We’re not just building for peak speed tests. We’re building a network that can handle the unpredictable, high-stakes moments that matter most to our customers. And we're doing it with some smart, behind-the-scenes engineering.
Engineering Deep Dive: Our "Secret Sauce" for Live Events

In the world of networking, big live-streamed events are a unique challenge. Many companies use their backbone network—the internet's "highways"—to deliver that content to customers. But we've taken a different approach. We are the first to host Google's live-optimized caching servers, which act like local content hubs right on our network.
During the São Paulo game, this approach proved its worth. At the traffic peak, our combined caches delivered over 750 Gbps of content, which accounted for more than 54% of the total. This massive cache delivery ensured our customers’ experience was seamless and reliable by keeping traffic local. Specifically, the new live-optimized node we deployed in Kansas City alone served over 280 Gbps. More recently, the total traffic served by Google's ecosystem (including platforms like YouTube and YouTube TV) hit a higher peak on September 30, with 1.67 Tbps of data served. Again, we were ready to meet the demand. Over 1 Tbps, or 62% of the traffic, was served by our cache servers. That’s a testament to the hard work of our engineering team.
But this story isn't just about handling a couple weeks of surging data; it's about our long-term strategy. 
The Data Check: What This Means for Your Experience

While peak speeds get the headlines, a network’s true quality is measured by its consistency and reliability. A network that delivers a smooth, buffer-free stream during the most intense moments is a network you can trust.
This is why we closely monitor data from third-party validators like Ookla. Our commitment to symmetrical fiber is evident in their speedtest data: nationally, our customers experience 684% faster uploads than the US average. Moreover, our latency is 41% better than the US average, giving you a more responsive, lag-free experience for everything from competitive gaming to video calls. That’s the result of our behind-the-scenes work on caching and network management. We’re obsessed with these metrics because they tell the real story of our network's performance.
Looking Ahead

Our work to provide a best-in-class network is never truly finished. We are not just building for tomorrow; we’re delivering it today. Virtually all GFiber customers currently have access to multi-gig speeds and roughly 90% of homes in our network are enabled for speeds up to 20 Gig. We are always looking ahead, paving the way for 50 Gig fiber connections and incorporating new technologies like Wi-Fi 7 and network slicing to ensure multi-gig speeds are delivered seamlessly whether you are gaming or streaming video. Watch this space, because we plan to share more insight into how these advancements are shaping the network of the future at GFiber.
Posted by John Keib, Chief Technology and Product Officer

Introducing Metrax: performant, efficient, and robust model evaluation metrics in JAX

Metrax is a high-performance JAX-based metrics library developed by Google. It standardizes model evaluation by offering robust, efficient metrics for classification, NLP, and vision, eliminating manual re-implementation after migrating from TensorFlow. Key strengths include parallel computation of "at K" metrics (e.g., PrecisionAtK) for multiple K values and strong integration with the JAX AI Stack, leveraging JAX's performance features. It is open-source on GitHub.

Making the terminal beautiful one pixel at a time

Google has launched the redesigned **Android AI Sample Catalog**, a dedicated, open-source application to inspire and educate Android developers on building AI-powered apps. It showcases examples using both on-device (Gemini Nano via ML Kit GenAI API) and Cloud models (via Firebase AI Logic SDK), including image generation with Imagen, on-device summarization, and a "Chat with Nano Banana" chatbot. The code is easy to copy and paste to help developers quickly start their own projects.

Introducing Code Wiki: Accelerating your code understanding

Code Wiki is a new platform that tackles the bottleneck of reading existing code by providing an automated, continuously updated, structured wiki for code repositories. It features hyper-linked documentation, a Gemini-powered chat agent that understands your repo, and automated diagrams. A public preview is available for open-source projects, and a Gemini CLI extension is coming soon for secure use on private repos.

Google Colab is Coming to VS Code

Google Colab has launched an official VS Code extension, bridging the gap between the popular code editor and the AI/ML platform. The extension combines VS Code's powerful development environment with Colab's seamless access to high-powered runtimes (GPUs/TPUs), allowing users to connect local notebooks to Colab. This aims to meet developers where they are and brings the best of both worlds.

Chrome Dev for Desktop Update

The Dev channel has been updated to 144.0.7524.3 for Windows, and 144.0.7524.0 for Mac and Linux.

A partial list of changes is available in the Git log. Interested in switching release channels? Find out how. If you find a new issue, please let us know by filing a bug. The community help forum is also a great place to reach out for help or learn about common issues.

Chrome Release Team
Google Chrome

Chrome Dev for Desktop Update

The Dev channel has been updated to 144.0.7524.3 for Windows, and 144.0.7524.0 for Mac and Linux.

A partial list of changes is available in the Git log. Interested in switching release channels? Find out how. If you find a new issue, please let us know by filing a bug. The community help forum is also a great place to reach out for help or learn about common issues.

Chrome Release Team
Google Chrome