Key takeaways
- AWS has introduced CodeWhisperer, a machine learning-powered coding assistant in technical preview.
- CodeWhisperer offers contextual recommendations based on the user's coding environment and previous code.
- The tool is compatible with various IDEs and supports popular programming languages like Python, Java, and JavaScript.
- CodeWhisperer is trained on extensive codebases, including open source and Amazon's internal repositories.
- Support for the AWS Lambda Console is forthcoming, expanding its usability.
Amazon Web Services has launched CodeWhisperer, a ML-powered coding companion, for technical preview. Trained on billions of lines of code and powered by machine learning, the CodeWhisperer helps students, developers and experienced professionals to be more productive by presenting syntactically correct recommendations as you code.
CodeWhisperer uses multiple contextual clues to drive recommendations including the cursor location in the source code, code that precedes the cursor, comments, and code in other files in the same projects. You can use the recommendations as-is, or you can enhance and customise them as needed. CodeWhisperer is trained (and continues to train) on billions of lines of code drawn from open source repositories, internal Amazon repositories, API documentation, and forums.
The preview form is supported for multiple IDEs and languages. To get started, you simply install the proper AWS IDE Toolkit, enable the CodeWhisperer feature, enter your preview access code, and start typing:
Source: amazon.com
