Amazon said CodeWhisperer uses ‘contextual clues’ to push recommendations and can help save time and effort for developers.
Amazon has launched a preview version of an AI-powered programming tool designed to help developers write code, similar to GitHub’s Copilot.
The tech giant said CodeWhisperer continually examines the code and attached comments, presenting “syntactically correct recommendations” based on the user’s coding style and variable names.
Amazon said the software can help save time and effort for developers, by helping them generate code to build and train their own machine learning models. The tool can also recommend unit test code that matches the developer’s implementation code.
The ability for coding assistant software to help developers has been showcased in GitHub’s AI AI-powered coding assistant, Copilot, which was made publicly available to developers earlier this week.
GitHub said the proportion of total code being written by the AI is on the rise. Last October, the company revealed that Copilot was helping write up to 30pc of code on the platform. Last week, the Microsoft-owned company said its AI assistant is helping write almost 40pc of code.
Amazon said its CodeWhisperer machine learning software was trained on billions of lines of code from the company’s internal repositories, along with open-source repositories, API documentation and public forums.
AWS VP and chief evangelist Jeff Barr said the software uses “multiple contextual clues” to push its recommendations including the cursor location, the code that precedes the cursor and code in other files of the same project.
A preview of the software is available as part of the AWS IDE Toolkit and works with Python, Java, and JavaScript. Amazon said CodeWhisperer supports multiple IDEs including VS Code, IntelliJ IDEA, PyCharm, WebStorm, and Amazon Web Services (AWS) Cloud9.
Amazon first announced CodeWhisperer at the Re: MARS AI conference in Las Vegas. This conference is also where the tech giant revealed it is working on technology that will give Alexa the ability to mimic virtually anyone’s voiceincluding the voice of a deceased relative.
The technology has raised eyebrows for its uses beyond just mimicking the voice of a dead person. For example, it could be used to deepfake the voice of living people for malicious purposes.
10 things you need to know direct to your inbox every weekday. Sign up for the Daily BriefSilicon Republic’s digest of essential sci-tech news.
