Coders are Furious About Github’s AI Assistant: Are they Overreacting?


AIBased on the Codex, this AI Assistant is the next step in a long line of “intelligent auto-completion” tools

Available as a downloadable extension, Github’s AI assistant, Copilot is powered by an AI model called Codex that’s trained on billions of lines of public code to suggest additional lines of code and functions given the context of existing code. Copilot can also surface an approach or solution in response to a description of what a developer wants to accomplish (e.g., “Say hello world”), drawing on its knowledge base and current context.

With Copilot, developers can cycle through suggestions for Python, JavaScript, TypeScript, Ruby, Go and dozens of other programming languages and accept, reject or manually edit them. Copilot adapts to the edits developers make, matching particular coding styles to autofill boilerplate or repetitive code patterns and recommending unit tests that match implementation code.

Copilot extensions are available for Noevim and JetBrains in addition to Visual Studio Code, or the cloud on GitHub Codespaces. One new feature coinciding with the general release of Copilot is Copilot Explain, which translates code into natural language descriptions. Described as a research project, the goal is to help novice developers or those working with an unfamiliar codebase.

Priced at US$10 per month or US$100 a year, GitHub Copilot is capable of suggesting the next line of code as developers type in an integrated development environment (IDE) like Visual Studio Code, Neovim, and JetBrains IDEs. Copilot can suggest complete methods and complex algorithms alongside boilerplate code and assistance with unit testing. More than 1.2 million developers signed up to use the GitHub Copilot preview over the past 12 months, and it will remain a free tool for verified students and maintainers of popular open-source projects. In files where it’s enabled, GitHub says nearly 40 percent of code is now being written by Copilot.

“Over the past year, we’ve continued to iterate and test workflows to help drive the ‘magic’ of Copilot,” Ryan J. Salva, VP of product at GitHub, told TechCrunch via email. “We not only used the preview to learn how people use GitHub Copilot but also to scale the service safely.”

“We specifically designed GitHub Copilot as an editor extension to make sure nothing gets in the way of what you’re doing,” GitHub CEO Thomas Dohmke says in a blog post(Opens in a new window). “GitHub Copilot distills the collective knowledge of the world’s developers into an editor extension that suggests code in real-time, to help you stay focused on what matters most: building great software.”

Dohmke says that 1.2 million developers tested Copilot(Which opens in a new window) during its technical preview. It seems that Copilot has proven to be quite the capable programmer, with Dohmke saying that for popular languages such as Python, devs are trusting Copilot to write as much as 40% of their code. (At least in files where it’s enabled; it accounts for a lower proportion in terms of total output.)


Must see news