Github recently announced at Build 2022 that Copilot, the service that provides code suggestions inside development environments like Microsoft Visual Studio, will be available free for students and “verified” open-source contributors. The technical preview of Copilot was available so far and is now planned to be generally made available this summer.
Copilot was launched by GitHub and OpenAI in June last year. The service is available as a downloadable extension. It is powered by an AI model called Codex that has been trained using billions of lines of public code to be able to suggest given existing coding context. It can also suggest an approach or a solution in response to a description of what a developer wants to accomplish, drawing on its knowledge base and current model.
General availability will not change the Copilot experience much and as it was with the technical review, developers will be able to cycle through suggestions for Python, JavaScript, TypeScript, Ruby, Go and dozens of other programming languages and accept, reject or manually edit them. The service adapts to the edits developers make, matches particular coding styles to autofill boilerplate or repetitive code patterns and recommends unit tests that match implementation code.
The extensions for Copilot are available for Noevim, JetBrains, Visual Studio Code, and in the cloud on GitHub Codespaces. Additionally, there is a new experimental feature the platform is working on called the Copilot Explain. This feature translates code into natural language descriptions to help novice developers or those working with an unfamiliar codebase.
Copilot Explain is an experiment and a part of a separate extension called Copilot Labs, a proving ground for experimental applications of machine learning that improve the developer experience. The “explain this code” and “translate this code” features are a part of this extension. Copilot Labs is intended to be experimental in nature so that things might break. Labs experiments may or may not progress into permanent features of GitHub Copilot, the platform explained.
