Google Launches Project IDX, a New AI-Enabled Browser-Based Development Environment (techcrunch.com) 17
An anonymous reader quotes a report from TechCrunch: Google today announced the launch of Project IDX, its foray into offering an AI-enabled browser-based development environment for building full-stack web and multiplatform apps. It currently supports frameworks like Angular, Flutter, Next.js, React, Svelte and Vue, and languages like JavaScript and Dart, with support for Python, Go and others in the works. Google did not build a new IDE (integrated development environment) when it created IDX. Instead, it is using Visual Studio Code -- Open Source as the basis of its project. This surely allowed the team to focus on the integration with Codey, Google's PaLM 2-based foundation model for programming tasks. Thanks to Codey, IDX supports smart code completion, a ChatGPT/Bard-like chatbot that can help developers with general coding questions as well as those related specifically to the code you are working on (including the ability to explain it) and the ability to add contextual code actions like "add comments."
"We spend a lot of time writing code, and recent advances in AI have created big opportunities to make that time more productive," the IDX team explains in today's announcement. "With Project IDX, we're exploring how Google's innovations in AI -- including the Codey and PaLM 2 models powering Studio Bot in Android Studio, Duet in Google Cloud and more -- can help you not only write code faster, but also write higher-quality code." As a cloud-based IDE, it's no surprise that Project IDX integrates with Google's own Firebase Hosting (and Google Cloud Functions) and allows developers to bring in existing code from the GitHub repository. Every workspace has access to a Linux-based VM (virtual machine) and, soon, embedded Android and iOS simulators right in the browser.
"We spend a lot of time writing code, and recent advances in AI have created big opportunities to make that time more productive," the IDX team explains in today's announcement. "With Project IDX, we're exploring how Google's innovations in AI -- including the Codey and PaLM 2 models powering Studio Bot in Android Studio, Duet in Google Cloud and more -- can help you not only write code faster, but also write higher-quality code." As a cloud-based IDE, it's no surprise that Project IDX integrates with Google's own Firebase Hosting (and Google Cloud Functions) and allows developers to bring in existing code from the GitHub repository. Every workspace has access to a Linux-based VM (virtual machine) and, soon, embedded Android and iOS simulators right in the browser.
Great, what's the robots.txt to restrict this? (Score:3)
Great, what's the robots.txt to restrict this from my web site?
Re: (Score:2)
I don't think you understood what it is.
You use this to make things like your web sites. It's an AI assisted dev tool. It removes the tedium from run of the mill web app and mobile app development.
Killed by Google (Score:3)
So anybody wanna give their best shot when this project will enter the Google graveyard? I give it two years.
Re: Killed by Google (Score:2)
Re: (Score:1)
Re: (Score:1)
IDX? (Score:3)
Are they supporting MUMPS as a backend language?
Re: (Score:3)
Are they supporting MUMPS as a backend language?
It currently supports frameworks like Angular, Flutter, Next.js, React, Svelte and Vue, and languages like JavaScript and Dart, with support for Python, Go and others in the works.
AI training data harvest tool (Score:5, Interesting)
Re: (Score:3)
From scraping code from stackoverflow to scraping the code directly from the developers' IDE.
For once, Google's trying to be efficient.
Re: (Score:2)
Frankly, developers should be building a lot more interesting things than just another CRUD app. I want AI to take those jobs. In the last 25 years, I think we have gone backwards in some ways in this area.
Re: (Score:1)
Re: (Score:2)
I understand its about making money first.
But won't you rather have dumb work automated and be able to look at the higher level aspects of the task, including integration. This is no different on having VM languages taking care of memory management so you can focus on business logic. There is just too much code now for basic data management apps, perhaps more so than there was 25 years ago, which the app addresses.