Large language model-based coding assistant GitHub Copilot will transition from using only 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 coming weeks. Google's Gemini 1.5 Pro will come 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 intended to be stronger at advanced reasoning than GPT-4, which Copilot has used so far. Developers will be able to switch between the models (even during a call) to tailor the model to their needs – and organizations will be able to choose which models can be used by team members.
The new approach makes sense for users because certain models are better at certain languages or types of tasks.
“There is no one model that covers 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 choice.”
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 offer multiple model choices for many of GitHub Copilot's surface areas and features,” Dohmke wrote.
There are also a handful of additional changes coming to GitHub Copilot, including extensions, the ability to manipulate 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-coders can use a series of natural language prompts to create simple apps, while coders can fine-tune as they go. In either case, you can take a conversational approach, requesting changes and iterating as you go, and comparing different iterations.
