GitHub launches Copilot to power pair programming with AI

Let the OSS Enterprise newsletter guide your open source journey! Sign up here.

GitHub has launched a new AI-powered pair programmer that collaborates with people on their software development projects, suggesting lines or entire functions as the coder types.

Pair programming, for the uninitiated, is a common agile software development technique where two (usually human) programmers work in tandem at a single screen, taking turns to write code and review the output of their partner.

GitHub Copilot

Copilot, as the new GitHub tool is called, uses contextual cues to suggest new code, with users able to flip through alternatives if they don’t like Copilot’s initial suggestion, or manually edit it. Copilot also learns over time, so that the more code, docstrings, comments, or function names a developer writes, the smarter Copilot should become.

Above: GitHub Copilot in action

Copilot is perhaps a little like Gmail’s smart compose feature, which suggests the next piece of text in an email response.

Machine power

The concept of what is effectively an AI-powered autocomplete for code is not entirely new. Codota and Tabnine have offered something similar for a while, and the two companies actually merged back in 2019 ahead of a $12 million fundraise for Codota. The duo finally settled on Tabnine as the main brand name last month.

More broadly, machine programming tools are rearing their heads across the spectrum, with Microsoft recently announcing a new Power Apps (software for creating low-code business apps) feature that leverages OpenAI’s GPT-3 language model to help users choose the right formulas.

Similarly, the new GitHub Copilot feature also leans heavily on a collaboration with OpenAI, the AI research company that GitHub parent Microsoft invested $1 billion in last year. Copilot, though, uses a new AI system called OpenAI Codex, which is touted as “significantly more capable than GPT-3 in code generation,” according to a GitHub blog post today. Given that it was trained on a dataset that incorporates more public source code, OpenAI Codex should be more knowledgeable about how developers write code and be able to make more accurate suggestions.

OpenAI Codex was also trained on both source code and natural language, meaning that it is able to interpret comments and logic when assembling the code.

Above: GitHub Copilot in action (find files)

While GitHub’s new AI pair programmer could help experienced developers save some time, it may prove particularly fruitful for coders new to a specific language or framework, as GitHub Copilot saves them from having to search elsewhere on the web for answers to their coding conundrums.

Availability

GitHub Copilot launches today 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. While Copilot is designed to work with a broad gamut of languages and frameworks, at launch it’s particularly adept at JavaScript, Python, Ruby, TypeScript, and Go.

It is worth noting that GitHub Copilot is not designed to write code on behalf of the developer;  it’s more about helping developers by understanding their intent. GitHub also gives no guarantees that the code it generates will even work, as it doesn’t test the code. This means that it may not compile properly. So there are some risks, but it’s still very early days for Copilot.