GitHub Copilot competitor: Google launches a chat tool for coding questions

Google has announced the launch of some AI-powered coding tools, including a competitor to GitHub Copilot, a chat tool for questions about coding and Google’s cloud services, and AI-powered code generation in AppSheet, a code-free product. The technology giant announced this during the annual I/O developer conference, writes TechCrunch.

Almost all of these new code completion and code generation tools are based on Codey. Based on Google’s extensive PaLM 2 language model, the company specifically trained Codey to handle coding-related hints. It also taught the model to handle requests related to Google Cloud as a whole.

Google explained that the model was trained on a large array of open code with a free license, as well as on a significant amount of the company’s internal code, all its code samples, and reference applications.

Developers will have access to these tools through extensions for Visual Studio Code, the JetBrains IDE, the Google Shell editor, and the Google Workstations cloud service. And although the model was trained in the context of Google Cloud, the code generation functions are not specific to the cloud platform. It supports Go, Java, JavaScript, Python, and SQL.

Developers will be able to chat with this model directly in their IDE or write a comment in a text file to have it generate the appropriate code. Compared to its competitors, Google’s tool stands out for its integration with the rest of Google’s cloud platform.

For now, only a small group of testers will be able to experience code assistance, integrated chat, and new AI integrations in Google’s AppSheet codeless development platform. Probably, more about all this will become known at the Google Cloud Next event at the end of August.

Soon, Google wants to use these models to help developers manage all their services on Google Cloud using this chatbot technology.

“In essence, I think we’ve been using 20th-century interfaces on 21st-century platforms. We’ve been doing CLI and UIs and APIs — those are awesome, but it’s a lot different than 50 years ago where it took a 50-page manual to use a computer. Now we’ve got over a million pages of Google Cloud docs. It’s time for something different,” said Google Cloud.

We will remind you that earlier Google merged its two main research groups into a division called Google DeepMind, which should accelerate research in the field of AI.