Skip to content
AI Coding Tools

GitHub Copilot moves beyond OpenAI models to support Claude 3.5, Gemini

News sparks speculation Microsoft will go multi-model with other AI products.

Samuel Axon – | 27
GitHub CEO Thomas Dohmke speaking at an event in 2022. Credit: Vaughn Ridley/Collision via Sportsfile
GitHub CEO Thomas Dohmke speaking at an event in 2022. Credit: Vaughn Ridley/Collision via Sportsfile

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

First, Anthropic's Claude 3.5 Sonnet will roll out to Copilot Chat's web and VS Code interfaces over the next few weeks. Google's Gemini 1.5 Pro will come a bit 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 until now. Developers will be able to switch between the models (even mid-conversation) to tailor the model to fit their needs—and organizations will be able to choose which models will be usable by team members.

The new approach makes sense for users, as certain models are better at certain languages or types of tasks.

"There is no one model to rule every scenario," wrote Dohmke. "It is clear the next phase of AI code generation will not only be defined by multi-model functionality, but by multi-model choice."

It starts with the web-based and VS Code Copilot Chat interfaces, but it won't stop there. "From Copilot Workspace to multi-file editing to code review, security autofix, and the CLI, we will bring multi-model choice across many of GitHub Copilot’s surface areas and functions soon," Dohmke wrote.

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

Ars Video

 

GitHub Spark promises natural language app development

In addition to the Copilot changes, GitHub announced Spark, a natural language tool for developing apps. Non-coders will be able to use a series of natural language prompts to create simple apps, while coders will be able to tweak more precisely as they go. In either use case, you'll be able to take a conversational approach, requesting changes and iterating as you go, and comparing different iterations.

Like Copilot Chat, GitHub Spark supports multiple models from OpenAI, Google, and Anthropic.

GitHub Spark is going into an early preview phase, but it won't be available to most people yet. Those interested in trying it out can join a waitlist.

Will Microsoft Copilot go multi-model?

GitHub Copilot was one of the first commercial AI tools to achieve widespread use in 2021, but Microsoft has since launched another tool called Copilot across multiple other products and contexts, adapting the same AI assistant approach to a wide range of products.

Microsoft has invested heavily in OpenAI, and like GitHub Copilot, Microsoft Copilot was built on OpenAI's various GPT models. However, the switch to a multi-model approach for GitHub Copilot raises questions about whether Microsoft will do the same for its other AI chat products aimed at non-developers.

It's not a sure thing. Microsoft acquired GitHub in 2018, but while that partnership has shown up in some integrations here and there, it seems to the outside observer that the tech giant has let GitHub operate fairly independently.

I'm told by multiple current GitHub employees that there have been cultural changes within the company that have frustrated longtime team members who preferred a more nimble startup approach.

Still, that doesn't mean that Microsoft's leadership believes that the multi-model approach fits its consumer AI products as well as it does GitHub. As I wrote earlier: This is particularly key for developers because various models are more or less effective at different languages, among other reasons. That difference is not always as pronounced for users who are, for example, tweaking emails or Word documents.

So, this move at GitHub doesn't confirm a coming change for Microsoft's wider world of AI products. It's something to watch, though. There have been reliable reports that Microsoft's leadership has become frustrated with the drama unfolding recently at OpenAI. And while most of Microsoft's biggest competitors haven't gone multi-model, some plan to. For example, Apple says it will launch iOS 18.2 in December with a major integration of OpenAI's ChatGPT—but it also said at its developer conference earlier this year that it would like to ultimately give users the option to choose other models, like Google's Gemini, to perform the same tasks.

Photo of Samuel Axon
Samuel Axon Senior Editor
Samuel Axon is a senior editor at Ars Technica, where he is the editorial director for tech and gaming coverage. He covers AI, software development, gaming, entertainment, and mixed reality. He has been writing about gaming and technology for nearly two decades at Engadget, PC World, Mashable, Vice, Polygon, Wired, and others. He previously ran a marketing and PR agency in the gaming industry, led editorial for the TV network CBS, and worked on social media marketing strategy for Samsung Mobile at the creative agency SPCSHP. He also is an independent software and game developer for iOS, Windows, and other platforms, and he is a graduate of DePaul University, where he studied interactive media and software development.
27 Comments
Prev story
Next story