How we developed Chrome’s first AI tools

Ai_Tools Image

Last year, the Chrome browser team brainstormed new ways to make Chrome helpful with AI; they knew large language models (LLMs) could create a better, easier browsing experience. “We’d been thinking about how to bring AI technology to the browser to make the typical actions you do every day — using tabs, using Search, writing in forms, reading webpages — a little easier,” says Chrome engineering director Adriana Porter Felt. “We solicited ideas from all over the Chrome team.” That brainstorm eventually led to the launch of three generative AI features for Chrome: AI themes, Tab organizer and help me write. AI themes for Chrome uses a text-to-image model to visually customize your Chrome browser. “Organize Similar Tabs,” or Tab organizer, intelligently groups browser tabs into categories to make your open web pages easier to find. And help me write crafts copy for your specific internet needs. “Back in 2008 when Chrome originally launched, the idea was to get content in front of a user and get the browser out of the way as much as possible,” Adriana says. But, she explains,
people’s browser habits have changed over time. Today, in many ways, people are looking for an assistant to help them along or speed up a process, like planning an upcoming vacation or filling out lengthy forms. “Now it’s about making things easier for users without getting in their way,” Adriana says. From an engineering perspective, implementing LLM technology into Chrome was a challenge. “It’s a new skill set,” Adriana says. “We had to learn not only how this technology works but also how to turn it into a product people can use. Traditional browser features work the same way every time you run them. If a feature has the same input, it will give the same output.” When Adriana and her team write code for a new Chrome feature, they also write tests to check it works as expected. “If it passes the tests, you have confidence it works,” she says. With features that use generative AI, it’s not so simple. Large language models recognize and generate text or images, and they need to be able to adapt to many kinds of user input. “We take the foundation model and we teach it what we want it to do for our example use cases, and then we evaluate how it works against many different types of user scenarios,” Adriana says. Read More

News Collect:

Mr. Shafiul Azam Bhuiyan

Student of Dhaka City College

Department of Business Administraion.