Google has launched a new video series called Build with Google AI. The series explains practical and useful projects based on artificial intelligence, which, according to Google, can be realized in less than a day.
According to the Google team, the projects don’t require deep knowledge of artificial intelligence, have modest developer requirements, and can be scaled up into useful solutions.
Google says AI models, including large language models like Google PaLM 2 and more specialized AI models for translation, object detection and other tasks, are at the heart of modern innovation, from self-driving cars to medical diagnostics. PaLM 2, or Pathways Language Model 2, is the latest generation of Google’s big language model. It’s an LLM with 540 billion parameters, trained on a huge dataset of code and multilingual texts in more than 100 languages.
The idea behind the new series of videos is that it’s not enough to just create new and better artificial intelligence models, it’s also important to create high-quality experiences and useful applications with them.
The first few videos in the series focus on leveraging the power of Google’s language models in applications, specifically the Google PaLM API. They are along the lines of “here’s the Google team, here’s how they created xxx, and here’s how you can extend it”. The introductory video describes how Google’s team of technical writers created a conversational search interface for their content based on artificial intelligence. The project looks at how to take this open source project and provide similar functionality for their own content.
The next project looks at how the People and AI Research team at Google created a storytelling app using artificial intelligence technology, and how you can extend their code to create your own storytelling app.
The third video explains how the AI Research team at Google created a code writing help agent as an extension for Visual Studio Code, and discusses how it can be extended.
Details of subsequent project videos have not yet been revealed, but Google says it will be a new set of projects running AI applications locally on devices to reduce latency, improve reliability, and improve data privacy.
You can find all of Google’s machine learning content at: https://ai.google/build/machine-learning/
What is Copy-On-Write
Copy-On-Write (COW) is a strategy used in computer programming and operating systems to optimize the performance and efficiency of memory...
Mobile App Development Best Practices – 11.12
Large photos in SwiftUI, Mutation Testing, Processing Payments in Firebase and more!
SDKs for which Apple will require a signature have been published
Apple has already listed SDKs commonly used in apps in the App Store that, from spring 2024, you will be...
Discover the Journaling Suggestions API
Journaling Suggestions is a visual picker interface for iPhone applications. It displays personal events that are happening in a person’s...
Tusky – An Android client for the microblogging server Mastodon
Tusky is a beautiful Android client for Mastodon. Mastodon is an ActivityPub federated social network. That means no single entity controls...
Swift 30 Projects: 30 mini Swift Apps for self-study
This repo is updated with Swift 5 and compatible with iPhone X: Simple UIKit components UIScrollView, UITableView, UICollectionView CAAnimations and...