27 results
APRIL 15, 2026 / Pay
Google has introduced enhancements to the Google Pay API to provide developers with greater flexibility and control over merchant-initiated transactions (MIT). The update includes new objects within the PaymentDataRequest to specifically handle recurring subscriptions, deferred payments like hotel bookings, and automatic account reloads. By allowing merchants to clearly define future payment terms, these changes improve transparency for users and help reduce transaction declines through better token management. Developers can now implement these features to create more seamless and secure long-term payment experiences.
MARCH 31, 2026 / AI
The newly introduced continuous checkpointing feature in Orbax and MaxText is designed to optimize the balance between reliability and performance during model training, addressing issues with conventional fixed-frequency checkpointing. Unlike fixed intervals—which can either compromise reliability or bottleneck performance—continuous checkpointing maximizes I/O bandwidth and minimizes failure risk by asynchronously initiating a new save operation only after the previous one successfully completes. Benchmarks demonstrate that this approach significantly reduces checkpoint intervals and results in substantial resource conservation, especially in large-scale training jobs where mean-time-between-failure (MTBF) is short.
MARCH 9, 2026 / Cloud
Wednesday Build Hour is a weekly, interactive "technical gym session" led by Google Cloud experts to help developers and architects sharpen their cloud skills. Moving beyond passive slide decks, the program focuses on hands-on building, covering advanced topics like AI agents, Vertex AI, and developer productivity tools. Each hour-long session is designed to provide tangible results that participants can immediately deploy into their own workflows. It serves as a consistent, dedicated space for builders to stay ahead of the curve and connect with a community of cloud engineers.
FEB. 19, 2026 / Gemini
The Android XR team is using Gemini's Canvas feature to make creating immersive extended reality (XR) experiences more accessible. This allows developers to rapidly prototype interactive 3D environments and models on a Samsung Galaxy XR headset using simple creative prompts.
FEB. 3, 2026 / AI
Finetuning the FunctionGemma model is made fast and easy using the lightweight JAX-based Tunix library on Google TPUs, a process demonstrated here using LoRA for supervised finetuning. This approach delivers significant accuracy improvements with high TPU efficiency, culminating in a model ready for deployment.
JAN. 16, 2026 / AI
FunctionGemma is a specialized AI model for function calling. This post explains why fine-tuning is key to resolving tool selection ambiguity (e.g., internal vs. Google search) and achieving ultra-specialization, transforming it into a strict, enterprise-compliant agent. A case study demonstrates the improved logic. It also introduces the "FunctionGemma Tuning Lab," a no-code demo on Hugging Face Spaces, which streamlines the entire fine-tuning process for developers.
OCT. 7, 2025 / AI
To avoid data bottlenecks when training large models, this guide introduces Grain and ArrayRecord for building high-performance data pipelines.
SEPT. 16, 2025 / AI
The Agent Development Kit (ADK) for Java 0.2.0 now integrates with LangChain4j, expanding LLM support to include third-party and local models like Gemma and Qwen. This release also enhances tooling with instance-based FunctionTools, improved async support, better loop control, and advanced agent logic with chained callbacks and new memory management.
SEPT. 4, 2025 / AI
Learn how to use Google's EmbeddingGemma, an efficient open model, with Google Cloud's Dataflow and vector databases like AlloyDB to build scalable, real-time knowledge ingestion pipelines.
AUG. 12, 2025 / Kaggle
Build and train a GPT2 model from scratch using JAX on Google TPUs, with a complete Python notebook for free-tier Colab or Kaggle. Learn how to define a hardware mesh, partition model parameters and input data for data parallelism, and optimize the model training process.
