GitHub and OpenAI preview AI tool that produces its own code

GitHub and OpenAI have launched a technical preview of a new AI tool called Github Copilot, which helps you write code more efficiently.

The aim of this feature is to learn how you write code, and to suggest lines and functions automatically. The Copilot tool also helps you find alternative ways to solve a problem and use, new APIs easily.

How does GitHub Copilot work?

GitHub Copilot is powered by OpenAI Codex, a new AI system created by OpenAI. OpenAI Codex was trained on publicly available source code and natural language, so it understands both programming and human languages. The GitHub Copilot editor extension sends your comments and code to the GitHub Copilot service, which then uses OpenAI Codex to synthesize and suggest individual lines and whole functions.

GitHub Copilot draws context from the code you’re working on and it helps you quickly discover alternative ways to solve problems, write tests, and explore new APIs without having to tailor a search for answers on the internet. As you type, it adapts to the way you write code—to help you complete your work faster.

“GitHub Copilot works with a broad set of frameworks and languages, but this technical preview works especially well for Python, JavaScript, TypeScript, Ruby and Go,” said CEO Nat Friedman.

While testimonials praise the productivity gains Copilot provides, GitHub implies that not all the code utilised was vetted for bugs, insecure practices, or personal data. The company writes they have put a few filters in place to prevent Copilot from generating offensive language, but it might not be perfect.

“Due to the pre-release nature of the underlying technology, GitHub Copilot may sometimes produce undesired outputs, including biased, discriminatory, abusive, or offensive outputs,” Copilot’s website says.

Will Copilot improve over time?

The company recently benchmarked it against a set of Python functions that have good test coverage in open source repos. They blanked out the function bodies and asked GitHub Copilot to fill them in. The model got this right 43% of the time on the first try, and 57% of the time when allowed 10 attempts. They stated ‘it’s getting smarter all the time.’ 

GitHub Copilot has launched in technical preview and is available as an extension for Microsoft’s cross-platform code editor Visual Studio Code, working locally or in the cloud.