Google’s Gemini Assistant is brilliant and frustrating

I don’t know how to say this, but sometimes the emotional labor of opening another app on your phone and typing some text is just too much.

I need to gather details about an Airbnb reservation from two different confirmation emails and send them to my friends. Or I want to find out when to leave this coffee shop to get home at a certain time via bus. These aren’t hard things to do, but they do require enough tapping on different apps or tabbing between screens that I start thinking, you know what? I don’t really need to send that email right now. I’ll just wing it and hope for the best with the bus schedule.

These are the jobs I want AI to take over for me. AI, including Google’s new Gemini Assistant, is not ready for it yet. But Gemini feels like a preview of this AI future can Look like – provided you are well integrated into Google services.

Gemini is Google’s AI chatbot, formerly known as bard, It’s an app you download from the Google Play Store, but that’s really it A piece of Google App It’s probably already on your phone if it runs Android. Once it’s up and running, you can replace the standard Google Assistant with Gemini and use it just like the old Assistant. But instead of just setting timers and telling you the weather, it can do everything Bard did – answer complex questions, make suggestions, and read your email if you let it.

That last part is important. However, Gemini is not as good at chatting as ChatGPT Its ability to connect to GmailGoogle Maps and Google Docs are what make it really interesting.

I asked her to summarize the details of that Airbnb reservation, and she did so – pulling information from two separate emails and putting it together into a short bullet point list. I then asked him to draft an email to my friends with all the details. Most of the time when I ask AI to write an email or text, the results are too embarrassing to actually send to anyone. To my surprise, it was fine.

It doesn’t really seem like much, but it’s the first time I’ve been really impressed with AI as a tool to help get things done. Maybe I lack imagination, but I get bored of ChatGPT very quickly; There are only so many times I can brainstorm business plans for retro arcades or ideas for vacations. i really need help pile of digital crap I am constantly moving forward for this live my life.

Unfortunately, Gemini doesn’t have that right now. I think it’s a mile more useful than the regular Assistant, and there’s a lot I like about it now. There is a small G icon below each answer you give, which allows you to search Google and fact-check Gemini’s work. This is important since AI sometimes has a tendency to make things up.

I also appreciate that when Gemini brings me something like a recipe or packing list, I have somewhere to put it. Gemini can export answers directly to Google Docs or Gmail. When I get the same things from ChatGPT, they seem like they’re floating around in space until I copy and paste them somewhere. They’re saved in your history, but you know what I mean.

However, Gemini is not adept at understanding context. I told him I was planning to ride my bike to the next neighborhood and asked him to suggest some things to do once I got there. It spit out an entire wall of text with suggestions that included, I kid you not, scuba diving, seeing live theater and gambling in a casino. Technically, you can do Do all of these things in Burien, Washington, but not all of a sudden in the middle of the day. They’re also not places I’d just casually ride my bike to.

In situations like this, the Gemini feels like a little “let me show Google Maps for you” machine. ChatGPT’s voice chat, on the other hand, suggested I go to some parks or coffee shops. also asked Me If I had something else in mind for my trip, and when I said I wanted to buy a book, she suggested a specific bookstore. so thoughtful! However, later on, Gemini’s Google Maps integration proved more useful: I asked for the bus route home, and Gemini gave me the correct route, whereas ChatGPT would have made me wait for the bus that leaves every 30 minutes. used to come.

Talking to Gemini feels like talking to a page of Google search results. If you say, “Hey Google” and ask it a question, it will answer you. Otherwise, you are just reading text. And it happens often Very of text; This assistant can use any editor. I’m also surprised that Gemini can’t access my calendar, but there is currently no extension for that as there is for Gmail and Docs. If I want to add something to my calendar, I have to go back to the regular Assistant. At that time, I will make a huge calendar program myself.

A decade ago, smart assistants like Siri and Alexa were touted as the next big means of interacting with our devices, but across the industry we’ve seen their progress stall. For now, Gemini is purely an optional accessory. But it’s also easy to see how it could eventually replace Google Assistant as the default, especially since Google is scaling back supporting features In recent history. We may have reached the limits of what non-AI voice assistants can do reliably.

To me, swapping out Gemini for the generic Google Assistant seems like a low-risk bet. I trained myself a long time ago not to use voice assistants because they are never able to do what I want them to do. Gemini can still set my timer and tell me if it’s going to rain, so why not bet on something better to help me in my day to day? Hopefully it will learn some lessons from ChatGPT along the way. In the meantime, I have to take my scuba diving lessons.