InfoQ Homepage News
-
Google Supercharges Gemini 3 Flash with Agentic Vision
Google has added agentic vision to Gemini 3 Flash, combining visual reasoning with code execution to "ground answers in visual evidence". According to Google, this not only improves accuracy, but more importantly unlocks entirely new AI-driven behaviors.
-
LinkedIn Leverages GitHub Actions, CodeQL, and Semgrep for Code Scanning
LinkedIn has rebuilt its static application security testing (SAST) pipeline using GitHub Actions and custom workflows, enabling consistent, enforceable code scanning across thousands of repositories. The redesign improves security coverage, developer workflow, and observability while supporting the company’s shift-left strategy.
-
Datadog Integrates Google Agent Development Kit into LLM Observability Tools
Datadog recently announced that its LLM Observability platform now provides automatic instrumentation for applications built with Google's Agent Development Kit (ADK), offering deeper visibility into the behavior, performance, cost, and safety of AI-driven agentic systems.
-
MUI Releases Base UI 1 with 35 Accessible Components
Base UI 1.0 has officially launched! This unstyled React component library, backed by MUI, offers 35 accessible components with a commitment to long-term maintenance. With refined APIs and enhanced performance, it empowers developers to create custom designs effortlessly while ensuring robust accessibility out of the box.
-
Conductor Quantum Introduces Coda, a Natural Language Interface for Quantum Computing
Conductor Quantum has announced Coda, a natural language interface for running quantum programs on real quantum hardware. The system is positioned as a software layer that translates high-level user intent into executable quantum circuits.
-
OpenCode: an Open-source AI Coding Agent Competing with Claude Code and Copilot
Open-source AI coding tool OpenCode features a native terminal-based UI, multi-session support, and compatibility with over 75 models, including Claude, OpenAI, Gemini, and local models. In addition to its CLI tool, OpenCode is also available as a desktop app and and an IDE extension for VS Code, Cursor, and other tools.
-
Getting Feedback from Test-Driven Development and Testing in Production
Teams rely on strong unit and integration tests instead of end-to-end tests. Using TDD, pair programming, and good design, they ship small changes often, test in production for real feedback, and use feature toggles to reduce risk, Ola Hast and Asgaut Mjølne Söderbom mentioned in their talk about continuous delivery with pair programming.
-
Google Pushes for gRPC Support in Model Context Protocol
Google Cloud is bridging a critical gap for enterprises by introducing a gRPC transport package for the Model Context Protocol (MCP), enhancing integration for businesses already using gRPC. This game-changer reduces development friction, ensuring AI agents seamlessly connect with existing services while boosting performance and efficiency. Join the evolving landscape of AI integration!
-
LinkedIn Re-Architects Service Discovery: Replacing Zookeeper with Kafka and xDS at Scale
LinkedIn's engineering team successfully upgraded its legacy ZooKeeper service discovery platform to enhance scalability and performance. By leveraging Apache Kafka and the xDS protocol, the new architecture enables eventual consistency, supports multiple languages, and allows migration without downtime. Post-upgrade, latency vastly improved, facilitating hundreds of thousands of app instances.
-
Java Explores Carrier Classes to Extend Data-Oriented Programming Beyond Records
The OpenJDK Amber project has published a new design note proposing “carrier classes” and “carrier interfaces” to extend record-style data modeling to more Java types. The proposal preserves concise state descriptions, derived methods, and pattern matching, while relaxing structural constraints that limit records.
-
Vercel Introduces Skills.sh, an Open Ecosystem for Agent Commands
Vercel has released Skills.sh, an open-source tool designed to provide AI agents with a standardized way to execute reusable actions, or skills, through the command line.
-
Agent Trace: Cursor Proposes an Open Specification for AI Code Attribution
Cursor has published Agent Trace, a draft open specification aimed at standardizing how AI-generated code is attributed in software projects. Released as a Request for Comments (RFC), the proposal defines a vendor-neutral format for recording AI contributions alongside human authorship in version-controlled codebases.
-
Astro Announces Version 6 Beta with Redesigned Development Server and First-Class Cloudflare Workers
Astro 6 Beta transforms web development with a revamped server leveraging Vite's Environment API, first-class Cloudflare Workers support, and stable live content collections. Emphasizing performance and security, it enables real-time data updates and strong Content Security Policy support. Designed for content-driven sites, Astro remains framework-agnostic amidst breaking changes.
-
GitHub Reworks Layered Defenses After Legacy Protections Block Legitimate Traffic
GitHub engineers recently traced user reports of unexpected “Too Many Requests” errors to abuse-mitigation rules that had accidentally remained active long after the incidents that prompted them.
-
OpenAI Begins Article Series on Codex CLI Internals
OpenAI recently published the first in a series of articles detailing the design and functionality of their Codex software development agent. The inaugural post highlights the internals of the Codex harness, the core component in the Codex CLI.