GitHub Next has unveiled a project called Code Brushes which uses machine learning to update code “like painting with Photoshop”.
Using the feature, developers can “brush” over their code to see it update in real-time.
Several different brushes are included to achieve various aims. For example, one brush makes code more readable—especially important when coding as part of a team or contributing to open-source projects.
Here are the other included brushes:
- Add types
- Fix bug
- Debug (adds debugging statements)
- Make robust (improves compatibility)
Code Brushes also supports the creation of custom brushes. One example is a brush to make a form “more accessible” automatically.
“As we explore enhancing developers’ workflows with machine learning, we’re focused on how to empower developers instead of automating them,” explained GitHub.
“This was one of many explorations we have in the works along those lines.”
Code Brushes is powered by the controversial GitHub Copilot. Copilot uses technology from OpenAI to help generate code and speed up software development.
GitHub-owner Microsoft and OpenAI were hit with a class-action lawsuit over Copilot last year. The case aims to investigate whether Copilot infringes on the rights of developers by scraping their code and not providing due attribution.
“Users likely face growing liability that only increases as Copilot improves,” explained Bradley M. Kuhn of Software Freedom Conservancy earlier this year.
“Users currently have no methods besides serendipity and educated guesses to know whether Copilot’s output is copyrighted by someone else.”
Code Brushes has been added to the Copilot Labs Visual Studio Code extension. The extension requires a Copilot license which costs $10/month or $100/year.
(Photo by Marcus Urbenz on Unsplash)
Want to learn more about AI and big data from industry leaders? Check out AI & Big Data Expo taking place in Amsterdam, California, and London.
Explore other upcoming enterprise technology events and webinars powered by TechForge here.
