Google is currently testing “Skills” for Gemini in Chrome, which will enhance the AI’s capabilities to perform tasks automatically within the browser. Gemini, now available on desktop in the US, acts as a helpful assistant, allowing users to summarize content, clarify confusing sections, and compile information from multiple tabs. For instance, if you have tabs open for flights, hotels, and activities, Gemini can extract key details to create a cohesive plan. Google intends to evolve Gemini into a fully-fledged agent in Chrome, with a dedicated “Skills” feature accessible via the page chrome://skills, where users can add and customize tasks for the AI. While this feature is under internal testing, its rollout timeline remains uncertain. Ultimately, Gemini aims to improve navigation by enabling natural language queries to locate previously visited pages and integrate seamlessly with Google apps like Calendar, YouTube, and Maps, enhancing user experience and efficiency.
Source link
Share
Read more