← More

More Tech

• Google is testing AI chatbot search for YouTube

  Google is trying out an AI Mode-like search experience for YouTube. The company is now testing "a new way to search on YouTube that feels more like a conversation," with results pulling in things like longform videos, YouTube Shorts, and text about what you're searching for. The "experiment" is now available if you're a YouTube Premium subscriber in the US who is 18 or older. I turned it on for my account. Now, in the search bar, I see an "Ask YouTube" button, and clicking the search bar shows prompts to ask like "funny baby elephant playing clips," "summary of the rules of volleyball," and "short history of the Apollo 11 moon landing." If … Read the full story at The Verge.

• NASA’s X-59 Gets Freedom 250 Logo

  NASA’s X-59 is helping the nation celebrate the 250th anniversary of its independence with an update to its livery – its official paint job and insignia. The one-of-a-kind research aircraft is the centerpiece of NASA’s Quesst mission to demonstrate technology to fly supersonic, or faster than the speed of sound, without generating loud sonic booms. […]

• Agents CLI in Agent Platform: create to production in one CLI

  Google Cloud has introduced the Agents CLI, a specialized tool designed to bridge the gap between local development and production-grade AI agent deployment. The CLI provides coding assistants with machine-readable access to the full Google Cloud stack, reducing context overload and token waste during the scaffolding process. By streamlining evaluation, infrastructure provisioning, and deployment into a single programmatic backbone, the tool enables developers to move from initial concept to a live service in hours rather than weeks.

• Developer’s Guide to AI Agent Protocols

  This blog post introduces a suite of six protocols, such as MCP and A2A, designed to eliminate custom integration code by standardizing how AI agents access data and communicate. Using a "kitchen manager" agent as a practical example, it demonstrates how these tools handle complex tasks like real-time inventory checks, wholesale commerce via UCP, and secure payment authorization through AP2. By leveraging the Agent Development Kit (ADK), developers can also implement A2UI and AG-UI to deliver interactive dashboards and seamless streaming interfaces to users.

• Closing the knowledge gap with agent skills

  To bridge the gap between static model knowledge and rapidly evolving software practices, Google DeepMind developed a "Gemini API developer skill" that provides agents with live documentation and SDK guidance. Evaluation results show a massive performance boost, with the gemini-3.1-pro-preview model jumping from a 28.2% to a 96.6% success rate when equipped with the skill. This lightweight approach demonstrates how giving models strong reasoning capabilities and access to a "source of truth" can effectively eliminate outdated coding patterns.