Tag: Google

A practical guide to debugging and profiling JAX on Cloud TPUs. It outlines core components (libtpu, JAX/jaxlib) and essential techniques. Tools covered include: Verbose Logging (via libtpu env vars), TPU Monitoring Library for performance metrics, tpu-info for real-time utilization, XLA HLO Dumps for compiler debugging, and the XProf suite for in-depth performance analysis.

ADK introduces **Context Engineering** to scale AI agents beyond large context windows. It treats context as a compiled view over a tiered, stateful system (**Session, Memory, Artifacts**). This architecture uses explicit processors for transformation, enables efficient compaction and caching, and allows for strict, scoped context handoffs in multi-agent workflows to ensure reliability and cost-effectiveness in production.

Gemini 3 Pro Preview is introduced as a powerful, agentic model for complex, (semi)-autonomous workflows. New agentic features include `thinking_level` for reasoning control, Stateful Tool Use via Thought Signatures, and `media_resolution` for multimodal fidelity. It has Day 0 support for open-source frameworks like LangChain, AI SDK, LlamaIndex, Pydantic AI, and n8n. Best practices include simplifying prompts and keeping temperature at 1.0.

The JAX AI Stack is a modular, industrial-grade, end-to-end machine learning platform built on the core JAX library, co-designed with Cloud TPUs. It features key components like JAX, Flax, Optax, and Orbax for foundational model development, plus an extended ecosystem for the full ML lifecycle and production. This integration provides a powerful, scalable foundation for AI development, delivering significant performance advantages.

Jules, an always-on, multi-step software development agent, now features Gemini 3, offering clearer reasoning and better reliability. Recent improvements include parallel CLI runs, a stable API, and safer Git handling. Upcoming features include directory attachment without GitHub and automatic PR creation. Jules aims to reduce software writing overhead so developers can focus on building.

Introducing Google Antigravity, a new agentic development platform for orchestrating code. It combines an AI-powered Editor View with a Manager Surface to deploy agents that autonomously plan, execute, and verify complex tasks across your editor, terminal, and browser. Agents communicate progress via Artifacts (screenshots, recordings) for easy verification. Available now in public preview.

LiteRT's new Qualcomm AI Engine Direct (QNN) Accelerator unlocks dedicated NPU power for on-device GenAI on Android. It offers a unified mobile deployment workflow, SOTA performance (up to 100x speedup over CPU), and full model delegation. This enables smooth, real-time AI experiences, with FastVLM-0.5B achieving over 11,000 tokens/sec prefill on Snapdragon 8 Elite Gen 5 NPU.

Gemini 3 is available via API with updates for developers: new `thinking_level` for depth control, `media_resolution` for multimodal processing, and enforced `Thought Signatures` for agentic workflows, especially with function calling and image generation. It also introduces combining Google Search/URL Grounding with Structured Outputs and new usage-based pricing for Grounding. Best practices, like using default temperature, are advised for optimal results.

The new Data Commons extension for the Gemini CLI makes accessing public data easier. It allows users to ask complex, natural-language questions to query Data Commons' public datasets, grounding LLM responses in authoritative sources to reduce AI hallucinations. Data Commons is an organized library of public data from sources like the UN and World Bank. The extension enables instant data analysis, exploration, and integration with other data-related extensions.

LiteRT and MediaTek are announcing the new LiteRT NeuroPilot Accelerator. This is a ground-up successor for the TFLite NeuroPilot delegate, bringing seamless deployment experience, state-of-the-art LLM support, and advanced performance to millions of devices worldwide.