Amazon AWS recently launched ML-powered coding companion CodeWhisperer which provides code recommendations based on comments from natural language developers and their code in the integrated development environment (IDE), the machine learning-powered service increases developer productivity.
CodeWhisperer bases its recommendations on several contextual clues, including the placement of the cursor in the source code, the code before it, comments, and code from other files in the same project. The recommendations can be implemented exactly as they are or can be improved and changed as needed. CodeWhisperer uses billions of lines of code from forums, internal Amazon repositories, open source repositories, and API documentation to train.
According to Amazon, developers can use CodeWhisperer to speed up the development process by simply adding a comment to the code in their IDE† The many programming languages, frameworks, software libraries and cloud services must be kept up-to-date. CodeWhisperer allows developers to speed up frontend and backend development with automatic code recommendations, save time and effort to generate code to build and train ML models, speed up the development process with code recommendations for AWS APIs for the most popular services , among which Amazon EC2† AWS Lambdaand Amazon S3and offload writing repetitive unit test code.
CodeWhisperer also places a strong emphasis on security, offering Python and Java scans to help programmers find vulnerabilities in their work and make apps accountable. In addition, it has a reference tracker that can determine if a code recommendation resembles a specific set of training data. Developers can then quickly locate the code sample, examine it, and choose whether to use it in their project.
According to Amazon, CodeWhisperer was not created to provide an alternative to: Second pilotseveral years ago, the company laid the foundation for launching services such as CodeGuru and DevOpsGuru†
For now, CodeWhisperer is compatible with Python, Java, and JavaScript. According to Amazon, it works with several IDEs, including: JetBrains† Visual Studio Code† AWS Cloud9and the AWS Lambda console.
Developers looking to test Amazon’s new code completion tool can: Sign Up for the waiting list by submitting an application form. Developers can use the AWS IDE Toolkitactivate the CodeWhisperer functionality and start using the tool after receiving a preview passcode.