Google has launched a new video series called Build with Google AI. The series is made up of AI-powered projects that Google says are practical and useful, and designed to be achievable in less than a day.

The Google team says the projects don't require deep knowledge of artificial intelligence, have modest requirements for development, and are extensible into useful solutions.

Google says that artificial intelligence models, including large language models like Google PaLM 2 and more focused AI models for translation, object detection, and other tasks are at the center of current innovations, from self-driving cars to medical diagnosis. PaLM 2, or Pathways Language Model 2, is the latest generation of Google's large language model. It is.a 540-billion parameter LLM trained on a massive dataset of code and multilingual text spanning more than 100 languages.

The thinking behind the new video series is that it's not enough to simply build new and better AI models, it is equally important to create high-quality experiences and helpful applications with those models.

The first few videos in the series focus on how to use Google's AI language model capabilities for applications, particularly the Google PaLM API. They take the form  of "here's a team at Google, here's how they built xxx, and here's how you can extend it." The opening video looks at how a technical writing team at Google built an AI-powered conversation search interface for their content. The project element of this looks at how to take that open source project and provide similar functionality for your own content.

The next project explains how the People and AI Research team at Google built a story writing application with AI technology, and how you can extend their code to build your own custom writing app.

The third video shows how the AI Developer Relations team at Google built a coding assistance agent as an extension for Visual Studio Code, and looks at how this could be extended.

Details of later videos in the project haven't been revealed yet, but Google says they will be a new set of projects that run artificial intelligence applications locally on devices for lower latency, higher reliability, and improved data privacy.

The first two parts of the series are available now.

More Information

Build with Google AI

Related Articles

Google's 25 Years of AI Progress

AI Advances At Google I/O

Google's Neural Networks See Even Better

TPU Is Google's Seven Year Lead In AI

Google Buys Unproven AI Company, Deep Mind

Why AlphaGo Changes Everything 

Can Google DeepMind Win At AI?

Google's Large Language Model Takes Control

To be informed about new articles on I Programmer, sign up for our weekly newsletter, subscribe to the RSS feed and follow us on Twitter, Facebook or Linkedin.

Comments

Make a Comment or View Existing Comments Using Disqus

or email your comment to: comments@i-programmer.info