product updateGitHub

GitHub Copilot CLI adds Rubber Duck for second-opinion AI suggestions

TL;DR

GitHub has added Rubber Duck to Copilot CLI, a feature that provides alternative suggestions by consulting different AI model families. The feature lets developers get a second opinion on code suggestions directly from the command line.

2 min read
0

GitHub Copilot CLI adds Rubber Duck for second-opinion AI suggestions

GitHub has expanded Copilot CLI with Rubber Duck, a new feature that generates alternative code suggestions by consulting different AI model families within the tool.

What is Rubber Duck?

Rubber Duck operates as a built-in second-opinion system for Copilot CLI. When developers request code suggestions or explanations in the terminal, Rubber Duck can provide an alternative perspective by leveraging a different model family than the primary suggestion engine. This gives users multiple approaches to the same problem without switching tools or contexts.

The feature is accessible directly from the CLI, maintaining the integrated workflow developers expect from GitHub's AI assistant.

Model Family Approach

The implementation reflects a deliberate architectural choice: rather than relying on a single model, GitHub's approach uses multiple model families to generate suggestions. This strategy acknowledges that different AI models have different strengths—some may excel at certain coding patterns, optimization techniques, or explanatory approaches.

GitHub has not disclosed which specific models or vendors power each model family in this implementation.

Developer Experience

The Rubber Duck feature integrates into Copilot CLI's existing workflow. When users request code suggestions, they can access the alternative perspective without manual intervention or additional configuration.

This addresses a common developer need: when the first suggestion doesn't feel right, having an immediate alternative saves context switching and maintains flow state. Rather than copying code to a separate chat interface or switching to the web version of Copilot, developers can iterate within their terminal.

What this means

GitHub is positioning Copilot CLI as a multi-model platform rather than a single-model tool. This approach distributes the technical risk of relying on one model while providing users with practical optionality. The Rubber Duck feature signals that GitHub views second opinions as core to code generation—not a luxury feature, but a workflow necessity. For developers already using Copilot CLI, this represents expanded capability at no apparent additional cost.

Related Articles

product update

Google AI Plus at $4.99/month and AI Pro at $19.99/month expand Gemini context windows to 128K and 1M tokens

Google has detailed pricing and features for its Gemini app subscription tiers. AI Plus costs $4.99/month and includes 128,000 token context windows, while AI Pro at $19.99/month provides 1 million token context windows. Free users are limited to 32,000 tokens.

product update

AWS launches MiniMax M2 family on Amazon Bedrock with 1M token context and MoE architecture

Amazon Web Services has added three MiniMax models to Amazon Bedrock: M2, M2.1, and M2.5. The newest model, M2.5, uses a mixture-of-experts architecture with 230 billion total parameters and 10 billion active per token, trained specifically for agent-native execution and coding tasks.

product update

AWS Ships Multi-Turn RL Infrastructure for Amazon Nova on SageMaker HyperPod

AWS has released infrastructure for deploying multi-turn reinforcement learning to train Amazon Nova models on SageMaker HyperPod. The system requires a minimum of 10 ml.p5.48xlarge instances and costs approximately $786-$1,180 per hour when running.

product update

AWS launches Nova-powered PII redaction pipeline for images using SAM 3 and Textract

AWS has released an automated pipeline for redacting personally identifiable information in images, using Amazon Nova 2 Lite as an intelligent coordinator. The solution combines Nova's contextual vision reasoning with Meta's SAM 3 model deployed on SageMaker and Amazon Textract to handle complex PII detection scenarios including faces, fingerprints, ID cards, and license plates.

Comments

Loading...