The Linux kernel now has official documentation covering AI assistant use: mandatory human responsibility, Assisted-by attribution tags, and full GPL and DCO compliance.

Bitrig now lets iOS developers build and test iPhone Duo apps using an interactive 3D simulator, following Apple's Xcode 27.1 beta 1 release.

Coder's new Agent Relay lets regulated enterprises run Claude Code inside their own cloud, VPC, or on-prem environment. Anthropic handles billing; your infra stays yours.

AI agents can scaffold an API integration fast, but reliable odds products need contracts, mock data, stable IDs, and recoverable streams. Here is what to check.

HA Dev Tools is an MIT-licensed HACS integration that connects MCP-capable AI assistants to Home Assistant automations, sensors, and dashboards with propose-then-confirm safety gates.

Bend 2 built a 442-line LLM proof system to solve a problem that SPARK resolves with 12 checks. The gap is a case study in skipping research before shipping.

AIR researchers found a zero-click remote code execution flaw in four major AI coding agents. Patches are out for Claude Code and Codex. GitHub Copilot is still unpatched.

AgentGit is an open source tool that applies version control to Claude Code and other agent sessions so teammates can resume work without rebuilding context from scratch.

Grant Fritchey's AI app build series reaches part six: a switch from Microsoft CoPilot to Claude, a cross-database term lookup feature, and an agent that initialized a database without being asked.

Anthropic updated Claude Code to support AGENTS.md as a fallback instruction file, aligning with the cross-tool standard already used in over 60,000 repositories.

OpenSpec and the Fission-AI workflow require markdown specs before any code runs, cutting hallucinations and context loss in AI-driven development. Version 1.13.1 now out.

A correct answer from your coding agent doesn't mean you measured model knowledge. Here's why sandbox design determines whether your eval result is valid.