GitHub is every developer’s best friend, especially if they’re working on an open source project, which is one of the reasons Microsoft swooped in.
At its recent Microsoft Build 2022 event, GitHub announced some pretty cool updates for one of its most interesting services: Copilot, the AI-powered feature that helps suggest code during the writing process.
Created in tandem with OpenAI, Copilot is effectively the coding helper of dreams, trained on a huge amount of raw code, helping developers spot issues, automate repetitive coding tasks, and more.
Github Copilot
“GitHub Copilot, released in a technical preview in June 2021, today suggests about 35% of the code in popular languages like Java and Python generated by the tens of thousands of developers in the technical preview who regularly use GitHub Copilot,” Microsoft said.
The big news from Build is that Copilot will be available more generally in summer 2022, including being made available to students for free. The exact details will be announced at a later date, but this seems like a promising development.
Microsoft says the overall experience of using Copilot won’t change much with general availability, such as working with Python, JavaScript, TypeScript, Ruby, and many other languages, suggesting edits and lines of code as the developer goes.
Work smart, not hard
As TechCrunch reports, one of the best innovations coming to Copilot is called Explain, offering natural language descriptions of code and what it does. Currently a research project, Explain could be a game changer.
“As a part of Copilot Labs, we launched ‘explain this code’ and ‘translate this code.’ This work fits into a category of experimental capabilities that we are testing out that give you a peek into the possibilities and lets us explore use cases,” GitHutb’s Ryan J. Salva told TechCrunch.
“Perhaps with ‘explain this code,’ a developer is weighing into an unfamiliar codebase and wants to quickly understand what’s happening. This feature lets you highlight a block of code and ask Copilot to explain it in plain language.”
“Again, Copilot Labs is intended to be experimental in nature, so things might break. Labs experiments may or may not progress into permanent features of Copilot.”
Of course, Copilot isn’t perfect and isn’t a panacea for creating beautiful code without a few touches of a button – doing something novel will require a lot of thought, debugging, and trial and error still.