Amazon has unveiled CodeWhisperer, a machine learning tool for developers designed to increase programmers productivity while mitigating risks such as prejudice, security, vulnerabilities, and bugs.
CodeWhisperer has a built-in security scanner to detect vulnerabilities in developers’ projects. It also has a built-in reference tracking function to see if a code recommendation resembles specific CodeWhisperer training data.
One of the remarkable features of CodeWhisperer is the ability to provide recommendations based on context-related information, such as the cursor location in the source code, the cursor of previous code, and the code in other files in the same project.
The tool responds to simple natural language prompts such as “upload a file with server-side encryption.”
CodeWhisperer also generates a complete subroutine at once and supports the most important programming languages such as Java, JavaScript and Python as well as several IDEs.
“We trained the model on the most common patterns for building cloud applications so you can build an innovate on the cloud much faster than ever before,” said Swami Sivasubramanian, AWS VP of data and ML services.