Large language model-based coding assistant GitHub Copilot will transition from exclusively using OpenAI's GPT models to a multi-model approach in the coming weeks, GitHub CEO Thomas Dohmke announced in a post on GitHub's blog.

First, Anthropic's Claude 3.5 Sonnet will be rolling out to Copilot Chat's web and VS Code interfaces in the next few weeks. Google's Gemini 1.5 Pro comes a little later.

Additionally, GitHub will soon add support for a wider range of OpenAI models, including GPT o1-preview and o1-mini, which are said to be stronger in advanced thinking than GPT-4, which Copilot has previously used. Developers can switch between models (even mid-conversation) to adapt the model to their needs – and organizations can choose which models to use by team members.

The new approach makes sense for users because certain models are better suited to certain languages ​​or task types.

“There is no model that governs every scenario,” Dohmke wrote. “It is clear that the next phase of AI code generation will be defined not only by multi-model functionality, but also by multi-model selection.”

It starts with the web-based and VS Code Copilot chat interfaces, but it doesn't stop there. “From Copilot Workspace to multi-file editing to code review, security autofix, and the CLI, we will soon provide a selection of multiple models across many of GitHub Copilot's interface areas and features,” Dohmke wrote.

There are also a handful of additional changes to GitHub Copilot, including extensions, the ability to edit multiple files at once from a chat with VS Code, and a preview of Xcode support.

GitHub Spark promises natural language app development

In addition to the Copilot changes, GitHub announced Spark, a natural language tool for app development. Non-programmers will be able to use a range of natural language prompts to build simple apps, while programmers will be able to make more precise optimizations over time. In both use cases you can take a conversational approach, request changes and iterate over time and compare different iterations.