GitHub unveils multi-model AI features for Copilot

GitHub has introduced several new developments centred on giving developers more control over their development tools and enhancing its platform's AI-powered capabilities.

GitHub announced the evolution of its Copilot-powered developer platform by making it multi-model. This advancement allows developers to select from models provided by Anthropic, Google, and OpenAI. GitHub's initiative focuses on increasing developer agency and aims to cater to the specific needs of its users by offering a variety of models. The models available include Anthropic's Claude 3.5 Sonnet, Google's Gemini 1.5 Pro, and OpenAI's GPT-4o variants. Developers can switch between models while using GitHub Copilot to find the one that best fits their needs, although the default setting remains powerful for many applications.

As of today, Anthropic's Claude 3.5 Sonnet is already integrated with GitHub Copilot, while Google's Gemini 1.5 Pro will be accessible in the upcoming weeks. GitHub is committed to offering developers a wider range of model choices and plans to integrate multi-model options across more of its platform's functionalities.

GitHub CEO Thomas Dohmke commented, "In 2024, we experienced a boom in high-quality large and small language models that each individually excel at different programming tasks. There is no one model to rule every scenario, and developers expect the agency to build with the models that work best for them. It is clear the next phase of AI code generation will not only be defined by multi-model functionality, but by multi-model choice. Today, we deliver just that."

Another significant announcement from GitHub was the introduction of GitHub Spark, an AI-native tool designed to enable individuals to build customised web applications entirely in natural language. This means that even those without coding experience can create personal, fully functional web apps by using GitHub Spark.

Jared Kaplan, Co-Founder and Chief Scientist at Anthropic, expressed, "Claude 3.5 Sonnet excels at coding tasks and is broadly used by developers for its exceptional grasp of software engineering principles and ability to tackle complex programming challenges. We're integrating Claude 3.5 Sonnet with GitHub Copilot today to further our ongoing efforts to put our most advanced AI capabilities directly into developers' hands wherever they're needed and wherever they work. Through GitHub Copilot, Claude will help even more developers throughout the entire development process, from concept to deployment."

Thomas Kurian, CEO at Google Cloud, added, "Developers want a broad choice of models that are best-suited for development, including code generation, refactoring, and optimizing code. Gemini models excel at this and are accessible on widely used developer platforms and environments — including now with GitHub Copilot — so millions of developers globally can benefit from trusted, enterprise-grade AI through Google Cloud."

In addition to the multi-model offerings, GitHub outlined updates to its broader platform features, which include new functionalities in GitHub Copilot integrated into Visual Studio Code, Copilot Workspace, GitHub Models, and the Copilot Autofix feature. These updates will inject AI capabilities across the platform's full spectrum, addressing issues, pull requests, and builds to further enhance the developer experience.