CodeWhisperer is currently in preview as part of the AWS IDE Toolkit, and interested developers can experience it right away with their preferred integrated development environment.
This includes VS Code, IntelliJ IDEA, PyCharm, WebStorm, and Amazon’s own AWS Cloud 9, with support for the AWS Lambda console coming soon.
Before today’s official announcement, Vasi Philomin, vice president of Amazon’s AI services, emphasized that the company is not simply creating a replica of GitHub Copilot.
In fact, CodeWhisperer is built on years of technology from the company’s AI code reviewer, CodeGuru performance analyzer, and DevOps Guru tool for slot manipulation issues.
In order to maintain a high degree of secrecy, the project was initially only known to a small number of internal test members. But now, interested developers can use CodeWhisperer to easily check code comments and even recommend variable names based on their personal programming style.
It’s worth mentioning that CodeWhisperer also does something different than GitHub Copilot. On the one hand, although most of the code generated by the system is novel, it emphasizes the original license every time it generates a segment that is similar to an existing segment during training.
By putting the choice in the hands of the developer, CodeWhisperer helps alleviate potential copyright issues that may arise when using such tools.
Second, Philomin emphasized the security features of CodeWhisperer. Thanks to Amazon’s own large code base and extensive problem reporting experience, this AI programming aid scans code for potential security issues.
Finally, the CodeWhisperer team has worked hard to ensure that no biased code is generated (via deployment filters), resulting in a fairly neutral AI-assisted programming experience for developers.