AI

GitHub’s context-aware secret classifier improves detection quality, raises weighted acceptance by 11.5%, and reduces median scan execution time by 86%.

Developers aren’t becoming more careless; they’re being outpaced. The tools that let developers create more software should also take on more of the work of protecting it.

We’re launching ReviewBench, a benchmark for code review agents built on representative GitHub pull requests, multi-source ground truth, calibrated evaluation, and production-aligned metrics.

Learn to direct AI agents, critically review their output, and keep technical judgment at the center of your workflow.

From loop engineering to harnesses, squads, and open weights, the GitHub Podcast breaks down the AI terms showing up in developer conversations.

The cost of writing code dropped; the cost of owning it didn’t. A framework for deciding which changes are actually cheap in the AI era.

As contribution volume grows, mentorship signals are harder to read. The 3 Cs framework helps maintainers mentor more strategically… without burning out.

An inside look at repository-native orchestration with GitHub Copilot and the design patterns behind multi-agent workflows that stay inspectable, predictable, and collaborative.

Open source is hitting an “Eternal September.” As contribution friction drops, maintainers are adapting with new trust signals, triage approaches, and community-led solutions.

Explore the GitHub Blog’s top posts covering the biggest software development topics of the year.

Discover how advanced AI users are redefining software development—shifting from code producers to strategic orchestrators—through delegation, verification, and a new era of AI-fluent engineering.

GitHub Copilot’s next edit suggestions just got faster, smarter, and more precise thanks to new data pipelines, reinforcement learning, and continuous model updates built for in-editor workflows.

An interview with the leader of GitHub Next, Idan Gazit, on TypeScript, Python, and what comes next.