{"id":131239,"date":"2025-05-25T17:54:11","date_gmt":"2025-05-25T17:54:11","guid":{"rendered":"https:\/\/www.europesays.com\/uk\/131239\/"},"modified":"2025-05-25T17:54:11","modified_gmt":"2025-05-25T17:54:11","slug":"trying-out-gemini-in-chrome-leaves-me-wanting-more","status":"publish","type":"post","link":"https:\/\/www.europesays.com\/uk\/131239\/","title":{"rendered":"Trying out Gemini in Chrome leaves me wanting more"},"content":{"rendered":"

I spent my morning with Gemini in Chrome, the new integration that puts the AI-powered assistant right in your browser. Instead of going to the chatbot\u2019s web app, you can click the new Gemini button in Chrome\u2019s top-right corner to start a conversation \u2014 but the key difference is that the browser\u2019s built-in assistant<\/a> can \u201csee\u201d what\u2019s on your screen while you navigate the web.<\/p>\n

To me, Gemini\u2019s integration in Chrome seems like just the start of Google\u2019s mission to make its AI more \u201cagentic,\u201d<\/a> as I found myself wanting it to do more than it actually could. For now, you can only try out the early access version of Gemini in Chrome if you\u2019re an AI Pro or AI Ultra subscriber, and use either the Beta, Dev, or Canary version of Chrome.<\/p>\n

I started out by using Gemini to summarize some of the articles on The Verge, as well as even find some gaming-related news on the homepage, where it pointed out the new Game Boy games Nintendo added to its Switch Online service, the upcoming Elden Ring film adaptation, and Valve\u2019s massive Steam Deck update.<\/p>\n

\"\"<\/a><\/p>\n

But Gemini can only \u201csee\u201d what\u2019s on your screen, so I found that if you want it to summarize certain elements, like The Verge\u2019s comments section, you\u2019ll need to make it visible before the chatbot can provide a response. Gemini will follow you when you switch tabs, too, but it can only pull information from one at a time.<\/p>\n

If you don\u2019t feel like typing, Gemini in Chrome also lets you switch to its \u201cLive\u201d feature by selecting the button in the bottom-right corner of the dialogue box. From there, you can simply ask a question out loud, and Gemini will respond by speaking to you.<\/p>\n

\"Gemini\u2019s<\/a><\/p>\n

Gemini\u2019s summaries can get a bit lengthy for such a small window. Screenshot: The Verge<\/p>\n

I found this especially useful to use alongside YouTube videos, where I cued up a bathroom remodeling video and asked, \u201cWhat tool is he using?\u201d Gemini responded, \u201cIt looks like he\u2019s using a nail gun to fasten some wood pieces together.\u201d In another video, Gemini correctly identified a capacitor on a motherboard, along with the tweezers and hot air tool the YouTuber used to remove it. It can summarize videos and tell you about specific parts you haven\u2019t watched as well, but I found that this isn\u2019t always accurate if a video doesn\u2019t have labeled chapters that it can draw information from.<\/p>\n

Probably my favorite use case for the integration is having Gemini pull recipes from YouTube videos, so I didn\u2019t have to write the recipes down myself or search for a link in the description. It also came in handy when I asked it to point out the waterproof bags on an Amazon search page.<\/p>\n

\"Gemini<\/a><\/p>\n

Gemini wasn\u2019t always consistent, though. When I asked Gemini where MrBeast is during a video of him exploring ancient Mayan cities<\/a>, including Chich\u00e9n Itz\u00e1, it replied, \u201cI don\u2019t have access to real-time information, so I can\u2019t pinpoint MrBeast\u2019s exact current location.\u201d When I asked it again, it responded with the location listed in the video\u2019s description: Mexico. Another time, I asked Gemini for a link to buy a specific pair of pliers shown in a video, but Gemini again told me that it didn\u2019t \u201chave access to real-time information, including product listings or store inventories.\u201d However, Gemini provided me with links to other products when prompted.<\/p>\n

At times, I felt that Gemini\u2019s responses were just too long for just a little pop-up window in Chrome. You can extend it, but it doesn\u2019t leave much room on my MacBook Air\u2019s 13-inch display. Plus, one of AI\u2019s main selling points is that it\u2019s supposed to help you save time by providing quick and concise answers, which it doesn\u2019t always do unless I specifically ask for that. Gemini\u2019s follow-up questions, like whether I would like to know more about a particular topic, also got a bit repetitive.<\/p>\n

Even with these hiccups, I can easily see Google extending Chrome\u2019s Gemini integration beyond just simple questions and answers. Google wants its AI to become \u201cagentic,\u201d meaning it can perform tasks on your behalf, and Gemini in Chrome seems poised to one day adopt these kinds of features. After asking Gemini to summarize a restaurant\u2019s menu, for example, I even thought about asking it to place a pickup order \u2014 an agentic task it just can\u2019t do yet. In the future, I could even see it coming in handy by having it bookmark pages related to travel research for me, or maybe even finding and saving YouTube videos of different recipes to my Watch Later playlist. <\/p>\n

Google seems like it\u2019s getting closer to making that a reality with Project Mariner\u2019s \u201cAgent Mode\u201d coming to the Gemini app<\/a>, which will allow it to manage up to 10 tasks at once and search the web for you \u2014 and maybe one day, it will bring these capabilities to Gemini in Chrome, too.<\/p>\n

<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"I spent my morning with Gemini in Chrome, the new integration that puts the AI-powered assistant right in…\n","protected":false},"author":2,"featured_media":131240,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[3163],"tags":[323,1942,867,326,53,16,15],"class_list":{"0":"post-131239","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-artificial-intelligence","8":"tag-ai","9":"tag-artificial-intelligence","10":"tag-google","11":"tag-tech","12":"tag-technology","13":"tag-uk","14":"tag-united-kingdom"},"share_on_mastodon":{"url":"https:\/\/pubeurope.com\/@uk\/114569757598634713","error":""},"_links":{"self":[{"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/posts\/131239","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/comments?post=131239"}],"version-history":[{"count":0,"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/posts\/131239\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/media\/131240"}],"wp:attachment":[{"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/media?parent=131239"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/categories?post=131239"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/tags?post=131239"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}