Discover how Rubber Duck provides a different perspective to GitHub Copilot CLI.

The GitHub Blog provides updates, announcements, and insights from the world's leading software development platform, covering topics such as new features, community highlights, and industry trends. Developers can learn about GitHub's latest developments, best practices for collaboration, and tips for maximizing productivity on the platform.

GitHub Blog

GitHub Copilot CLI introduces 'Rubber Duck' in experimental mode, a cross-model review agent that uses a model from a different AI family to critique the primary agent's work. When using a Claude model as the orchestrator, Rubber Duck runs GPT-5.4 to independently review plans, implementations, and tests. Benchmarks on SWE-Bench Pro show Claude Sonnet + Rubber Duck closes 74.7% of the performance gap between Sonnet and Opus, with the biggest gains on complex multi-file tasks. Rubber Duck activates automatically at key checkpoints (after planning, after complex implementations, after writing tests) and can also be triggered on demand via the /experimental command.

GitHub Copilot CLI combines model families for a second opinion

The problem: Confident mistakes can compound