Microsoft’s parent company, GitHub has set a new pace for coding with Claude 3.5 Sonnet, Gemini 1.5 Pro, and OpenAI’s o1 models.
Developers will have the flexibility to switch between models (even during a conversation) to customise the model to their requirements, while organisations can select which models team members can use.
The new approach benefits users since specific models are superior for particular languages or tasks.
In a recent blog post, GitHub CEO Thomas Dohmke announced that GitHub Copilot will begin using a multi-model approach instead of relying solely on OpenAI’s GPT models.
The rollout will begin with Anthropic’s Claude 3.5 Sonnet for Copilot Chat’s web and VS Code interfaces in the upcoming weeks, while Google’s Gemini 1.5 Pro will follow soon after.
Thomas Dohmke added in a statement, “In the past year, we experienced a boom in high-quality small and large language models that individually excel at different programming tasks. It is clear the next phase of AI code generation will not only be defined by multi-model functionality, but by multi-model choice. GitHub is committed to its ethos as an open developer platform, and ensuring every developer has the agency to build with the models that work best for them. Today at GitHub Universe, we delivered just that.”
Also added, “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.”
It is notable that GitHub previously shared guidelines for using the GitHub Copilot Workspace.
GitHub has announced Spark, a new natural language tool for app development, in conjunction with the Copilot updates. Non-coders can use prompts to build simple applications, while coders will have the ability to make precise tweaks as they go.
This conversational method allows users to request changes and compare different iterations.
Anyone wishing to try it can join the waitlist.