If you’ve been diligently keeping your Chromebook updated with the latest versions of ChromeOS you might have noticed a new “star” icon that’s appeared on the Shelf (taskbar). It’s a shortcut to Google Gemini generative AI. And it’s pretty cool…
Microsoft was the first company to leap into the pervasive AI world by adding its Copilot button to the Windows 11 Taskbar. Built on OpenAI’s ChatGPT, it turns out to be quite convenient to have a button click away, not to mention its smooth integration into Microsoft Edge, the new default browser for all Windows users. Generative AI doesn’t have to be creating things for you, however, it’s just as capable of answering questions or synthesizing information to respond to a query that you might have given to Google earlier. The difference? Usually much better and more understandable results (with an occasional glitch, so be cautious).
Artificial Intelligence has expanded by leaps and bounds in the last few years, so it’s no surprise that every company is now trying to integrate AI into its products. AI cars? Check. AI phones? Check. AI-powered doorbells, bicycles, televisions, lights, toys, headphones? Check. It’s no surprise that the ChromeOS development team wanted to offer up the same capabilities to Chromebook users. Just because you’re on what was intended to be a super low cost computer, doesn’t mean you shouldn’t have all these features!
And so, Gemini has arrived onto your Chromebook’s Shelf (what Windows users call a Taskbar and Mac users call a Dock. Why they can’t all have the same name is a debate for another article!). To get started, update your Chromebook to the very latest version of ChromeOS.
CLICK THE BUTTON, DUDE!
Once you’ve updated, you’ll see a new button on your Shelf. Right-click on it:
Remember that if you’d rather not have Gemini taking up valuable Shelf space, you can always Unpin it with this submenu. Instead, just click on it to launch Gemini. You’ll probably get this update:
We’ll check out the new image generation capabilities with Imagen 3 in a bit, but for now, what’s important is to start by being mindful of privacy and security issues. Click on “Done” to remove the notification.
GEMINI AI AND GOOGLE PRIVACY SETTINGS
Google knows that privacy is a significant issue so first launch of Gemini includes this alert:
First off, you can see on the left side that I already use Gemini on other devices. As with most every other app nowadays, Google shares your prompts (what AI people call queries) across devices. This means that it’s saving your prompts. For how long? Is it using them for training future updates to Gemini? That’s what the warning is about:
“Humans review some saved chats to improve Google AI. To stop this for future chats, turn off Gemini Apps Activity. If this setting is on, don’t enter info you wouldn’t want reviewed or used.”
I can’t help wonder if that’s also true of Google searches or even Gmail searches: Are humans reading those too? It certainly reminds us that privacy is important. So much so that it’s worth exploring further.
GEMINI ON CHROME AND PRIVACY
Start by clicking on “Manage Activity”. If you don’t see the above prompt, no worries, go into Settings > Apps and find Gemini to get to the below screen:
There are a few things you can tweak on this screen that help you ensure that Gemini is accessing the data and devices that you desire and not those that you don’t. For example, it can be helpful for the program to have access to your location for localized query answers, but you might prefer to leave that disabled, as shown above.
The more interesting setting is reached by clicking on the “How it Works” link or going to myactivity.google,com/product/gemini directly. It has this explanation:
The question here is whether you want Gemini storing your queries for months or even years? To see your options, click on “Turn off“…
You can see that the choices are to turn off logging (for longer than 72 hours) or to turn off logging and delete and stored activity. Which are you comfortable with for your own interactions with Gemini? Click on the appropriate button to make that choice. If you opt to turn this off, you’ll get a warning:
Be prepared for Gemini to be cranky about this decision if you opt to turn off Apps Activity logging. Nothing overt, but it will keep warning you that you aren’t getting “the full experience”. Me? I can live with that. Now, let’s have a bit of fun.
CREATING IMAGES IN GEMINI AI
Now that we’ve done the heavy work of setting up preferences and privacy settings for Gemini, the main window is finally ready for a query. I’ll start by asking it create a picture of a kitten typing on an apple MacBook pro with dramatic lighting, cyberpunk.
Explanation: The phrase “create a picture of” lets Gemini know about the desired output (an image, not words), then I use very specific details as desired to accurately describe the output I seek (apple MacBook pro). It’s always good to include a few cues about the style of artwork too, so I have “dramatic lighting” and “cyberpunk”.
Here’s how that works out for me:
Notice on the left it’s complaining that “Gemini Apps Activity is off”. Hopefully that goes away after a while.
The image is pretty solid, but the kitten’s a bit too cute for the image created. What’s wonderful about the chat-style interface of GPT systems is that you can clarify what you seek rather than type in the entire query a second time. I do, typing give the kitten an eye patch and a leather jacket. The results are pretty sweet:
There ya go, a memorable feline tough-gal image produced by Google Gemini AI directly on a budget Lenovo Chromebook. Now it’s your turn!
Pro Tip: I’ve been writing about AI and ChromeOS for quite a while. You can find a lot more useful tutorials in both my AI and ChatGPT help library and Chrome OS and Chromebook help library here on the site. Why not check them out while you’re visiting?