GitHub, the leading platform for software development collaboration, has announced today the next step in AI-driven software development with the introduction of Copilot X. As a pioneer in the use of generative AI for code completion, GitHub is now taking its partnership with OpenAI further by adopting the latest GPT-4 model and expanding Copilot’s capabilities.
Launched less than two years ago, GitHub Copilot has already made a significant impact on the world of software development. GitHub reported today that the AI-powered tool, built using OpenAI’s Codex model, currently writes 46% of the code on the platform and has helped developers code up to 55% faster. By auto-completing comments and code, Copilot serves as an AI pair programmer that keeps developers focused and productive.
A bold vision with chat
GitHub Copilot X, the upgraded version being released today, represents a bold vision for the future of AI-powered software development. With an emphasis on accessibility, the upgraded Copilot will now be available throughout the entire development life cycle, going beyond mere code completion. By incorporating chat and voice features, developers can communicate with Copilot more naturally. Additionally, Copilot X will be integrated into pull requests, command lines and documentation, providing instant answers to questions about projects.
The transformative potential of AI in software development is on full display with GitHub Copilot X. By reducing boilerplate and manual tasks, developers can focus on more complex and innovative work. This new level of productivity will allow developers to concentrate on the bigger picture, fostering innovation and accelerating human progress.
Event
Transform 2023
Join us in San Francisco on July 11-12, where top executives will share how they have integrated and optimized AI investments for success and avoided common pitfalls.
The developer experience reimagined with AI
GitHub Copilot X introduces several new features including a ChatGPT-like experience in code editors, Copilot for pull requests, AI-generated answers for documentation and Copilot for the command line interface.
Copilot chat builds upon the work that OpenAI and Microsoft have done with ChatGPT and the new Bing. GitHub brings a chat interface to the editor that’s focused on developer scenarios and natively integrates with VS Code and Visual Studio. It goes far beyond a chat window — Copilot X now recognizes what code a developer has typed and the error messages shown, and it’s deeply embedded into the IDE.
In addition to enhancing the editing experience, Copilot X allows Copilot to make pull requests. This feature is powered by OpenAI’s new GPT-4 model and supports AI-powered tags in pull request descriptions. It happens through a GitHub app that organization admins and individual repository owners can install. The tags are automatically filled out by Copilot based on the changed code, and developers can review or modify the suggested descriptions.
GitHub is also testing new capabilities internally where Copilot will automatically suggest sentences and paragraphs as developers create pull requests. Soon, Copilot will warn developers about insufficient testing for a pull request and suggest potential tests tailored to a project’s needs.
GitHub is also launching Copilot for docs, an experimental tool that uses a chat interface to provide users with AI-generated responses to questions about documentation, including questions about languages, frameworks and technologies. Initially, the company is focusing on documentation for React, Azure Docs, and MDN. Eventually, it plans to bring this functionality to any organization’s repositories and internal documentation, so developers can ask questions via a ChatGPT-like interface and receive instant answers.
In addition to the editor and pull request, GitHub has streamlined the terminal, where developers spend a significant amount of time. To help developers save time and effort, GitHub is releasing Copilot CLI, which can compose commands and loops, and handle obscure find flags to satisfy queries. Developers can join the waitlist to take advantage of this tool that translates natural language into terminal commands.