Amazon CodeWhisperer is now called Q Developer and is expanding its functions | TechCrunch

pour one out for codewhisperer, Amazon’s AI-powered assistant coding tool. To this day, it’s kaput – sort of.

codewhisperer is now q developerPart of Amazon’s Q family of business-oriented generative AI chatbots that also extends to the newly announced Q Business, Available through AWS, Q developer helps Some of the tasks that developers do in the course of their daily work, like debugging and upgrading apps, troubleshooting, and performing security scans – much like CodeWhisperer.

In an interview with TechCrunch, Doug Seven, GM and director of AI developer experiences at AWS, said that CodeWhisperer was a bit of a branding fail. Third-party metrics reflect as much, Even with one free level, CodeWhisperer struggled to match the pace of the main competitor GitHub Copilot, which has over 1.8 million paying individual users and thousands of corporate customers. ,bad initial impression Certainly didn’t help.)

“CodeWhisperer is where we started [with code generation]bWe really wanted a brand – and name – that was suitable for a broad set of uses,” Seven said. “You can think Q Developer is somewhat more comprehensive as an evolution of CodeWhisperer.

To that end, the Q developer can generate code including SQL, a programming language commonly used to create and manage databases, as well as test that code and change new code derived from developer queries. And can help in implementing.

Similar to Copilot, customers can fine-tune QDeveloper on their internal codebase to improve the relevance of the tool’s programming recommendations. (now obsolete CodeWhisperer … Offered This option too.) And, thanks to a capability called Agent, the Q developer can autonomously do things like implementing features and documenting and refactoring (i.e. reorganizing) code.

Ask a Q developer a request like “Create an ‘Add to Favorites’ button in my app,” and the Q developer will analyze the app code, generate new code if necessary, create a step-by-step plan, and complete testing. Code before executing the proposed changes. Developers can review and iterate on the plan, add steps, and apply updates to required files, code blocks, and test suites before Q implements it.

“What happens behind the scenes is that the Q developer actually sets up a development environment to work on the code,” Seven said. “So, in the case of feature development, the queue developer takes the entire code repository, creates a branch of that repository, analyzes the repository, does the work he’s been asked to do and commits those code changes to the developer. Returns.”

Image Credit: Amazon

Amazon says agents can also automate and manage code upgrading processes, with Java conversions live today (built specifically using Java 8 and 11). apache maven Java version 17) and .NET conversions are coming soon. Seven said, “The Q developer analyzes the code – looking for anything that needs upgrading – and makes all those changes before returning it back to the developer himself to review and commit. “

To me, Agents sounds a lot like GitHub copilot workbench, who similarly formulates and implements plans for bug fixes and new features in the software. And – like Workspace – I’m not entirely convinced that this more autonomous approach can solve the issues surrounding AI-powered coding assistants.

An analysis by GitClear of more than 150 million lines of code committed to project repos over the past several years revealed that Copilot resulting in more incorrect code Being pushed to the codebase. Elsewhere, security researchers have warned that CoPilot and similar devices could Exacerbating existing bugs and security issues in software projects,

This is not surprising. AI-powered coding assistants sound impressive. But they have been trained on existing code, and their suggestions reflect the work patterns of other programmers – work that may be seriously flawed. Assistants’ guesses create bugs that are often difficult to identify, especially when developers—who are adopting AI coding assistants a great number – Defer decisions to assistants.

In a low-risk area beyond coding, a Q developer can help manage a company’s cloud infrastructure on AWS – or at least get them the knowledge they need to manage it themselves.

Queue developers can fulfill requests like “List all my Lambda functions” and “List my resources living in other AWS regions.” Currently in preview, the bot can also generate (but not execute) AWS command line interface commands and answer AWS cost-related questions, such as “What were the top three highest cost services in Q1?”

amazon queue developer

Image Credit: Amazon

So how much do these generative AI features cost?

Q Developer is available for free in the AWS Console, Slack, and IDEs like Visual Studio Code, GitLab Duo, and JetBrains – but with limitations. The free version does not allow custom libraries, packages, and APIs, and selects users into the data collection scheme by default. It also imposes monthly limits, including a maximum of five agent tasks per month (e.g. deploying a feature) and 25 queries about AWS account resources per month. (It’s shocking to me that Amazon would put a limit on questions asked about its services, but here we are.)

The premium version of Q Developer, Q Developer Pro, costs $19 per user per month and includes higher usage limits, tools to manage users and policies, single sign-on, and – perhaps most importantly – IP compensation.

amazon queue developer

Image Credit: Amazon

In many cases, the models underpinning code-generating services like QDeveloper are trained on code that is under copyright or restrictive licenses. Vendors claim that fair use protects them in the event that the model was intentionally or unintentionally developed on copyrighted code – but not everyone agrees. GitHub and OpenAI are getting together filed a lawsuit against one in class action motion They have been accused of infringing copyright by allowing Copilot to re-release licensed code snippets without providing credit.

Amazon says it will protect Q Developer Pro customers from claims alleging that the service infringes third-party IP rights, as long as they let AWS handle their defense and “as AWS We dispose of it as we deem fit.