Amazon launches CodeWhisperer, a GitHub Copilot-like AI pair programming tool Meczyki.Net

In its Re-Mars conference, Amazon today announced The launch of CodeWhisperer, an AI pair programming tool similar to GitHub’s Copilot that can autocomplete entire tasks based on just a comment or a few keystrokes. The company trained the system, which currently supports Java, JavaScript, and Python, with billions of lines of publicly available open-source code and its own codebase, as well as publicly available documentation and code on public forums. Feather.

It is now available as part of a preview AWS IDE ToolkitWhich means developers can immediately use it inside their favorite IDEs, including Visual Studio Code, IntelliJ IDEA, PyCharm, WebStorm, and Amazon’s own AWS Cloud 9. Support for AWS Lambda Console is also coming soon.

Ahead of today’s announcement, Vasi Philomin, Amazon’s VP in charge of AI services, stressed that the company didn’t make it just to offer a copy of CoPilot. He said CodeGuru, its AI code reviewer and performance profiler, and DevOps Guru, with its tools for finding operation issues, laid the groundwork for today’s launch a few years ago, the company said.

image credit: heroine

,I Thinking technology Is Feather One point where We Thinking This was Correct Time To Doing This,” said Philomin.And This fit thoroughly with other pieces He they passed. it is Gone One journey And We right now What happened? Different Parts Feather Different Times.”

Internally, Amazon is testing the service with only a small number of developers — mostly to keep the announcement under wraps.

Pxl 20220623 161005990

image credit: heroine

The company notes that the system constantly checks your code and comments and even takes into account your own coding style and variable names. Using this contextual information—and where your cursor is—it will then generate its own custom code snippet.

It’s worth noting that CodeWhisperer does a few things apart from the likes of Copilot. For one, while most of the code that the system generates is novel, each time it generates code close to the existing snippet in its training data, it will take note of that and uncover the license of that original function. It is then up to the developer whether to use it or not. This should alleviate some (though probably not all) of the copyright concerns that probably come with using such a tool.


image credit: heroine

Another factor Philomin emphasized is safety. Based on Amazon’s own experience managing large codebases and debriefing after things go bad (using its formality)correction of errors‘ process), as well as its experience with CodeGuru, CodeWhisper will scan the code for potential security issues.

“Security is always important at AWS and so we want to make sure the code we generate is secure,” Philomin said. “Now obviously we’ve got the code ready and the developer can change it – and so CodeWhisper has the ability to say: Run a scan on the current source file. This I’ll do the security scan and it will show you what’s generated or replaced.” Will let you know about any issues and security vulnerabilities in the code.


image credit: heroine

Philomin also emphasized that the team worked hard to ensure that the code that CodeWhisperer generates also does not generate any biased code. However, when it does, the team has implemented filters to automatically remove that code.

The actual user/developer experience is pretty straightforward. Developers can choose between different code suggestions (the demos I saw usually had at least two options). It can autocomplete comments and based on only those comments, it will suggest actions. A simple example for this would be something like # check if a number is prime,

And while the system will work fine for developers outside the AWS ecosystem, Philomin said the team took great care to make sure it would work great for developers who want to use it to access AWS services. are (think Create #S3 Bucket,

“When we say it has first-class support for AWS APIs, it’s just extra stuff. In terms of all our measurements and all of our tests, we find it to be remarkably well done and it will be state-of-the-art, “They said. Since developers can test the service now, we’ll hear soon about how well it works and how it compares to projects like CoPilot. If anything, though, it’s great to have more options in this space (and someone’s definitely going to hack a project that will automatically provide suggestions from multiple pair programming AIs).