GitHub's new Rubber Duck feature in Copilot CLI adds a second AI model from a different family to review code plans.

DevOps publication provides insights into DevOps practices, tools, and culture, offering articles and tutorials for automating software delivery pipelines and fostering collaboration between development and operations teams. By exploring DevOps's curated content, developers can learn about infrastructure as code (IaC), containerization, and cloud-native technologies for building scalable and resilient applications. DevOps publication offers  guidance and best practices to accelerate your software delivery process and improve team collaboration.

DevOps.com

GitHub has introduced an experimental Copilot CLI feature called Rubber Duck that pairs a primary AI model with a reviewer from a different AI family to catch errors the primary model might miss. When Claude Sonnet 4.6 is the primary orchestrator, GPT-5.4 acts as the reviewer. Testing on SWE-Bench Pro showed this pairing closes 74.7% of the performance gap between Sonnet and Opus, at lower cost. Rubber Duck triggers automatically at three checkpoints — after planning, after complex implementation, and after writing tests — and can also be invoked manually. The feature is available now via the /experimental slash command in GitHub Copilot CLI.

GitHub Copilot CLI Gets a Second Opinion — and It’s From a Different AI Family