Google code homepage
ADK for Java opening up to third-party language models via LangChain4j integration
The recent 0.2.0 release of Google’s Agent Development Kit (ADK) for Java adds an integration with t...
Beyond the terminal: Gemini CLI comes to Zed
Google and Zed have partnered to integrate Gemini CLI directly into the Zed code editor, bringing AI capabilities directly into the editor for developers and allowing for faster and more focused coding, enabling tasks like in-place code generation, instant answers, and natural chat within the terminal with a seamless review workflow for AI-generated changes.
Meet Jules’ sharpest critic and most valuable ally
Jules' critic functionality addresses potential issues like subtle bugs and missed edge cases in AI-generated code by acting as a peer reviewer within the generation process. This "critic-augmented generation" means proposed code changes undergo adversarial review, allowing Jules to improve its output and ultimately deliver higher-quality, pre-reviewed code.
Gemini CLI + VS Code: Native diffing and context-aware workflows
The latest Gemini CLI update provides a deep IDE integration within VS Code for intelligent, context-aware suggestions, and native in-editor diffing, allowing developers to review and modify proposed changes directly within the diff view for a more efficient workflow.
Introducing Gemma 3 270M: The compact model for hyper-efficient AI
Google's new Gemma 3 270M is a compact, 270-million parameter model offering energy efficiency, production-ready quantization, and strong instruction-following, making it a powerful solution for task-specific fine-tuning in on-device and research settings.
Announcing Imagen 4 Fast and the general availability of the Imagen 4 family in the Gemini API
Google announces the general availability of Imagen 4, its advanced text-to-image model, in the Gemini API and Google AI Studio, featuring significant improvements in text rendering. The new Imagen 4 Fast model, designed for speed and rapid image generation, is now available alongside Imagen 4 and Imagen 4 Ultra, with Imagen 4 and Imagen 4 Ultra also supporting up to 2K resolution image generation.
URL context tool for Gemini API now generally available
The Gemini API's URL Context tool is now generally available, allowing developers to ground prompts using web content instead of manual uploads. This release expands support to PDFs and images.
What's new in Gemini Code Assist
Gemini Code Assist's Agent Mode, now available in VS Code (Preview) and IntelliJ (Stable), streamlines complex coding tasks by proposing detailed plans for user review and approval. This intelligent, collaborative approach, enhanced with features like inline diffs and persistent chat history, aims to boost developer productivity and efficiency.
Introducing Gemini 2.5 Flash Image, our state-of-the-art image model
Gemini 2.5 Flash Image is a new state-of-the-art image generation and editing model that allows for blending multiple images, maintaining character consistency, and targeted transformations using natural language, leveraging Gemini's world knowledge, now available through the Gemini API, Google AI Studio, and Vertex AI.
Stop “vibe testing” your LLMs. It's time for real evals.
Stax, an experimental developer tool, addresses the insufficient nature of "vibe testing" LLMs by streamlining the LLM evaluation lifecycle, allowing users to rigorously test their AI stack and make data-driven decisions through human labeling and scalable LLM-as-a-judge auto-raters.