Most developer tools to date have relied on human skills to build applications, but that could soon change, thanks in no small part to the rise of AI-based services.
GitHub Copilot, an AI-powered Coding Assistant, is Publicly Available
On June 21, Microsoft’s GitHub division announced widely available Copilot, its AI-assisted code development tool. The GitHub Copilot service was first announced as a technical preview in June 2021, and 1.2 million users had signed up during the pilot period.
During the GitHub Universe 2021 Event last OctoberBrian Douglas, GitHub’s director of developer advocacy, explained that artificial intelligence in Copilot provides developers with suggestions for writing code functions. GitHub Copilot works with multiple code development tools, including Microsoft Visual Studio, Neovim, and JetBrains.
As a widely available service, GitHub Copilot is free for both students and popular open source projects. For everyone else, GitHub Copilot costs $10 per month or $100 per year.
“GitHub Copilot distils the collective knowledge of the world’s developers into an editor extension that suggests code in real time so you can focus on what matters most: building great software,” CEO of GitHub Thomas Dohmke wrote in a blog post.
Amazon CodeWhisperer opens preview for AI-assisted development
GitHub Copilot isn’t the only AI-powered programming tool: Just two short days after Copilot’s launch, Amazon Web Services (AWS) announced its proprietary technology on June 23.
Amazon CodeWhisperer, like GitHub Copilot, takes advantage of machine learning AI to predict and generate the code developers look for when building applications in a developer tool. It can run in the AWS Cloud9 integrated development environment (IDE) and in third-party IDEs, including Microsoft Visual Studio and JetBrains.
CodeWhisperer goes a step further than just suggesting code, but will also suggest how a developer can connect to AWS APIs to take advantage of the cloud vendor’s various services, such as AWS Lambda for serverless functions and Amazon S3 for storage.
“CodeWhisperer is trained on a variety of data sources, including Amazon.com and open source code, and generates code similar to how a developer would write code,” says the function documentation for CodeWhisperer states. “The service understands comments written in plain natural language, generates code based on developer intent, and fits the developer’s patterns and style.”
While CodeWhisperer is AWS’s first AI-powered tool specifically for writing new code, it’s not the first time AWS has used artificial intelligence to help with developers’ workflows.
In 2019 AWS announced its: Amazon CodeGuru service, which uses AI to optimize code with best practices. At the AWS re:Invent 2020 event, the cloud giant announced its DevOps Guru service, which uses AI to provide suggestions and optimization for the DevOps workflow.
About the authorSean Michael Kerner is an IT consultant, technology enthusiast and tinkerer. He advises industry and media organizations on technology issues.