Microsoft-owned open-source developer platform GitHub has announced the launch of Copilot X, the company’s vision for the future of AI-powered software development.
GitHub has adopted OpenAI’s new GPT-4 model, and introduced chat and voice for Copilot, bringing Copilot to pull requests, the command line, and docs to answer questions on developers’ projects.
“From reading docs to writing code to submitting pull requests and beyond, we’re working to personalise GitHub Copilot for every team, project, and repository it’s used in, creating a radically improved software development lifecycle,” Thomas Dohmke, CEO at GitHub, said in a statement.
“At the same time, we will continue to innovate and update the heart of GitHub Copilot — the AI pair programmer that started it all,” he added.
The company is bringing a chat interface — “Copilot chat” to the editor, which will be focused on developer scenarios and natively integrate with VS Code and Visual Studio.
Copilot chat will recognise what code a developer has typed, and what error messages are shown, and it’s deeply embedded into the IDE (Integrated Development Environment).
Copilot chat will also join GitHub’s voice-to-code AI technology extension the company previously demoed, which it’s now calling “Copilot voice”, where developers can verbally give natural language prompts, according to the company.
Moreover, developers can now sign up for a technical preview of the first AI-generated descriptions for pull requests on GitHub.
This new feature comes powered by OpenAI’s new GPT-4 model and adds support for AI-powered tags in pull request descriptions via a GitHub app that can be installed by organisation admins and individual repository owners.
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 developers have about the languages, frameworks, and technologies they are using, the company said.