At GitHub, our mission has at all times been to innovate forward of the curve and provides builders all the things they have to be happier and extra productive in a world powered by software program. When we started experimenting with giant language fashions a number of years in the past, it shortly turned clear that generative AI represents the way forward for software program improvement. We partnered with OpenAI to create GitHub Copilot, the world’s first at-scale generative AI improvement instrument made with OpenAI’s Codex mannequin, a descendent of GPT-3.
GitHub Copilot began a brand new age of software program improvement as an AI pair programmer that retains builders within the circulate by auto-completing feedback and code. And lower than two years since its launch, GitHub Copilot is already writing 46% of code and helps builders code as much as 55% quicker.
But AI-powered auto-completion is simply the place to begin. Our R&D crew at GitHub Next has been working to maneuver previous the editor and evolve GitHub Copilot right into a readily accessible AI assistant all through all the improvement lifecycle. This is GitHub Copilot X—our imaginative and prescient for the way forward for AI-powered software program improvement. We aren’t solely adopting OpenAI’s new GPT-4 mannequin, however are introducing chat and voice for Copilot, and bringing Copilot to tug requests, the command line, and docs to reply questions in your tasks.
With AI accessible at each step, we are able to essentially redefine developer productiveness. We are decreasing boilerplate and handbook duties and making complicated work simpler throughout the developer lifecycle. By doing so, we’re enabling each developer to focus all their creativity on the massive image: constructing the innovation of tomorrow and accelerating human progress, immediately.
Let’s soar in.
Want to see what’s new? Discover GitHub Copilot X—our imaginative and prescient for the way forward for AI-powered software program improvement. Learn extra >
A brand new AI-powered developer expertise 🧑💻
- A ChatGPT-like expertise in your editor with GitHub Copilot Chat: We are bringing a chat interface to the editor that’s targeted on developer eventualities and natively integrates with VS Code and Visual Studio. This does excess of recommend code. GitHub Copilot Chat isn’t just a chat window. It acknowledges what code a developer has typed, what error messages are proven, and it’s deeply embedded into the IDE. A developer can get in-depth evaluation and explanations of what code blocks are meant to do, generate unit checks, and even get proposed fixes to bugs.
GitHub Copilot Chat builds upon the work that OpenAI and Microsoft have accomplished with ChatGPT and the brand new Bing. It can even be part of our voice-to-code AI technology extension we beforehand demoed, which we’re now calling GitHub Copilot Voice, the place builders can verbally give pure language prompts.
Sign up for the technical preview >
- Copilot for Pull Requests: You can now join a technical preview of the primary AI-generated descriptions for pull requests on GitHub. This new performance is powered by OpenAI’s new GPT-4 mannequin and provides assist for AI-powered tags in pull request descriptions via a GitHub app that group admins and particular person repository house owners can set up. These tags are mechanically crammed out by GitHub Copilot primarily based on the modified code. Developers can then assessment or modify the recommended description.
Enroll your repository within the technical preview >
This is simply step one we’re taking to rethink how pull requests work on GitHub. We’re testing new capabilities internally the place GitHub Copilot will mechanically recommend sentences and paragraphs as builders create pull requests by dynamically pulling in details about code modifications.
We are additionally getting ready a brand new function the place GitHub Copilot will mechanically warn builders in the event that they’re lacking ample testing for a pull request after which recommend potential checks that may be edited, accepted, or rejected primarily based on a challenge’s wants.
This enhances our efforts with GitHub Copilot Chat the place builders can ask GitHub Copilot to generate checks proper from their editor—so, within the occasion a developer might not have ample take a look at protection, GitHub Copilot will alert them as soon as they submit a pull request. It can even assist challenge house owners to set insurance policies round testing, whereas supporting builders to satisfy these insurance policies.
- Get AI-generated solutions about documentation: We are launching GitHub Copilot for Docs, an experimental instrument that makes use of a chat interface to offer customers with AI-generated responses to questions on documentation—together with questions builders have in regards to the languages, frameworks, and applied sciences they’re utilizing. We’re beginning with documentation for React, Azure Docs, and MDN, so we are able to be taught and iterate shortly with the builders and customers of those tasks.
We’re additionally working to deliver this performance to any group’s repositories and inner documentation—so any developer can ask questions by way of a ChatGPT-like interface about documentation, idiomatic code, or in-house software program of their group and get immediate solutions.
We know that the advantages of a conversational interface are immense, and we’re working to allow semantic understanding of everything of GitHub throughout private and non-private information bases to higher personalize GitHub Copilot’s solutions for organizations, groups, firms, and particular person builders alike primarily based on their codebase and documentation.
Moving ahead, we’re exploring the most effective methods to index sources past documentation reminiscent of points, pull requests, discussions, and wikis to offer builders all the things they should reply technical questions.
- Copilot for the command line interface (CLI): Next to the editor and pull request, the terminal is the place the place builders spend essentially the most time. But even essentially the most proficient builders must scroll via many pages to recollect the exact syntax of many instructions. This is why we’re launching GitHub Copilot CLI. It can compose instructions and loops, and throw round obscure discover flags to fulfill your question.
Let’s construct from right here 🚀
From studying docs to writing code to submitting pull requests and past, we’re working to personalize GitHub Copilot for each crew, challenge, and repository it’s utilized in, making a radically improved software program improvement lifecycle. Together with Microsoft’s information mannequin, we’ll harness the reservoir of knowledge and insights that exist in each group, to strengthen the connection between all employees and builders, so each concept can go from code to actuality with out friction. At the identical time, we’ll proceed to innovate and replace the guts of GitHub Copilot—the AI pair programmer that began all of it.
GitHub Copilot X is on the horizon, and with it a brand new era of extra productive, fulfilled, and comfortable builders who will ship higher software program for everybody. So—let’s construct from right here.