I spent my morning with Gemini in Chrome, the new integration that holds the AI-manual assistant in your browser. Instead of going to the chatbot’s web app, you can click on the new Gemini button in Chrome’s top-right corner to start a conversation-but the important difference is what the browser has on your screen while navigating the inherent assistant web.
For me, the integration of Gemini in Chrome seems to be the beginning of Google’s mission to make my AI a more “agent”, as I found that I wanted to do more than I could actually do myself. For now, you can only try the initial access version of Gemini in Chrome if you are AI Pro or AI Ultra subscribers, and use the beta, deva or canary version of Chrome.
I started using Gemini to summarize some articles. RuckusAlso find some gaming-related news on homepage, where it added new game Boy Games Nintendo to his switch online service, upcoming. Alden ring Film adaptation, and large -scale steam deck updates of the valve.
But Gemini only on your screen, “can see”, so I found that if you want it to summarize some elements, like, like RuckusComment section, you will need to make it visible before the chatbot provides a response. When you switch the tab, Gemini will still follow you, but it can only draw information from one at a time.
If you do not mind typing, Gemini in Chrome also selects the button in the lower-right corner of the dialog box and lets you switch to the “live” feature. From there, you can just ask a question, and Gemini will answer with you.
I found it especially useful to use with YouTube videos, where I cited a bathroom remodeling video and asked, “What equipment is he using?” Mithun replied, “It seems that he is using a nail gun to connect some wooden pieces together.” In another video, Mithun correctly identified a capacitor on a motherboard, as well as youtuber with tweezers and hot air tools to remove it. This can summarize the video and tell you about the specific parts you have not even seen, but I found that it is not always accurate if a video does not have labeled chapters that it can draw information.
Possibly the case of my favorite use for integration is in Gemini Bridge Recipes from YouTube video, so I did not need to write dishes myself or search for a link in details. It was also used even when I asked it to indicate the waterproof bag on the Amazon search page.
Gemini was not always consistent, though. When I asked Mithun where is Mrbeast A Video of searching ancient maya citiesWith Chichen Itza, it replied, “I do not have access to real -time information, so I cannot indicate the exact current location of MRbeast.” When I asked it again, it replied with the location listed in the details of the video: Mexico. Another time, I asked Mithun for a link to buy a specific pair shown in a video, but Mithun again told me that he did not have access to real -time information including “product listing or store inventory.” However, Gemini indicated me when links to other products were indicated.
Sometimes, I felt that Gemini’s reactions for only a little pop-up window in Chrome were very long. You can increase it, but it does not leave much space on my McBook Air’s 13 -inch display. In addition, one of the main sales points of AI is that it is going to help save time by providing you quick and brief answer, which does not always do it until I specifically ask for it. Mithun’s follow -up questions, such as if I would like to know more about a particular subject, also got a little repetition.
Even with these hiccups, I can easily see Google expanding the Gemini integration of chrome beyond simply simple questions and answers. Google wants his AI to become “agent”, which means it can function on your behalf, and Gemini in Chrome is ready to adopt such characteristics one day. For example, after asking Mithun to summarize the menu of a restaurant, I also thought of asking to give it a pickup order – an agent work that it could not do yet. In the future, I could also see that it is working with bookmark pages related to travel research for me, or perhaps to find and save YouTube videos of various dishes for the playlist later.
Google feels that this project is getting closer to a reality with the merrinner’s “agent mode” to enter the Gemini app, which will allow it to manage 10 tasks at once and find a web for you – and perhaps one day, it will also bring these abilities to Mithun in Chrome.
