Technology

GitHub Copilot Expands with Multi-Model Support

Published October 30, 2024

Developers, rejoice: You'll soon be able to use several new large language models (LLMs) in GitHub Copilot, the company's coding assistant.

On Tuesday at its annual GitHub Universe conference, the Microsoft subsidiary announced support for four new LLMs in Copilot: Claude 3.5 Sonnet, Gemini 1.5 Pro, and OpenAI's o1-preview alongside o1-mini. The OpenAI models are available now in Copilot Chat, with Claude 3.5 Sonnet up next, followed by Gemini 1.5 Pro "in the coming weeks," according to the announcement.

Also: You could win $25,000 for pushing Google's Gemini 1.5 to its limit

From Copilot Workspace to multi-file editing to code review, security autofix, and the CLI, many of GitHub Copilot's areas will soon support multi-model choices, the company noted.

GitHub first launched Copilot utilizing Codex, an early version of OpenAI's GPT-3. Last year, GitHub introduced Copilot Chat, initially with GPT-3.5, followed by GPT-4. The company mentions that it has consistently updated its underlying models based on quality and latency needs, offering a mix of models from GPT-3.5 Turbo to GPT-4o mini.

According to GitHub, there has been a significant increase in the capabilities of both small and large LMs to address various programming requirements.

"The next phase of AI code generation will not only be characterized by multi-model functionality, but also by multi-model choice," GitHub stated in the announcement. "GitHub is dedicated to its open developer platform ethos, ensuring every developer has the freedom to work with the models that suit them best."

Also: OpenAI plans to offer its 250 million ChatGPT users even more services

The company also introduced GitHub Spark, an AI tool allowing users to build applications using natural language. With this tool, users can create Sparks, or "micro apps," that utilize AI and external data without consuming cloud storage. An early preview registration is available at GitHub Spark.

Future of AI Development

As the landscape of AI in coding evolves, GitHub's introduction of multi-model support reflects a broader shift towards customization and flexibility in software development. This enhances the development experience by allowing users to select models that align with their specific needs and workflows.

Conclusion

With these advancements, GitHub Copilot aims to redefine how developers interact with coding tools, fostering a more inclusive and adaptable environment for all types of programmers.

GitHub, AI, Copilot