Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Putting Gemini to Work in Chrome

blog.google

Post reply on HN
Print view View original

51–60 of 64 posts

Re: Putting Gemini to Work in Chrome

#51

Post by cguess »

walletdrainer wrote: post #16
hackyhacky wrote: post #5

Serious question, not snark: Does anyone actually want this? I honestly can't imagine a use for these features even among people tech savvy enough to understand them.

I use AI-controlled browsers for everyday tasks like “Find me a Michelin starred restaurant in Paris with availability for 4 people at 8PM today”. Also for things like locating a product available to pick up in a nearby store, it’s crazy how often Google fails at this particular task.

I mean, if you don't care at all about cuisine, style, location etc. I guess? Searching is half the fun of something like that.

Anyways I will (continue to) not touch Chrome with a 1000ft pole after this. AI is awful in almost every aspect I've ever tasked it to.

Re: Putting Gemini to Work in Chrome

#52

Post by tmaly »

I was trying to use Gemini connected apps with YouTube to get details about my channels performance. It could not do it, I instead had to settle for what it could see publicly on my channel.

Re: Putting Gemini to Work in Chrome

#53

Post by xnx »

ed_mercer wrote: post #32

> We’re also bringing the creative power of Nano Banana directly into Chrome, allowing you to transform images on the fly without needing to download and re-upload images or open another tab. Are there really people who are like "Man, if only I could this straight in Chrome" ? Is this something worth bloating a browser (further) with?

Yes. AI is the next abstraction layer. By analogy, instead of wielding the wrench (application) yourself, you have a plumber (AI) fix your pipes. The browser is just a rich interface to that AI.

Re: Putting Gemini to Work in Chrome

#54

Post by xnx »

cguess wrote: post #51
walletdrainer wrote: post #16

Earlier quoted context omitted.

I use AI-controlled browsers for everyday tasks like “Find me a Michelin starred restaurant in Paris with availability for 4 people at 8PM today”. Also for things like locating a product available to pick up in a nearby store, it’s crazy how often Google fails at this particular task.

I mean, if you don't care at all about cuisine, style, location etc. I guess? Searching is half the fun of something like that. Anyways I will (continue to) not touch Chrome with a 1000ft pole after this. AI is awful in almost every aspect I've ever tasked it to.

> I mean, if you don't care at all about cuisine, style, location etc. I guess?

You can always ask for a list and still make the final decision yourself.

Re: Putting Gemini to Work in Chrome

#55

Post by xnx »

coffeefirst wrote: post #49
jsnell wrote: post #12

Earlier quoted context omitted.

Basically none of their examples are just "browse a page"? They're multi-step tasks combining data from multiple pages. Like the first example in the demo carousel (the Y2K party) starts from a photo and a prompt of roughly "buy the props needed for replicating this photo from Etsy". It first analyzes the image in the current tab, identifies a bunch of things to buy, searches for them on Etsy, customizes the orders,…

Maybe I’m a curmudgeon who can’t imagine throwing an elaborate Y2K party because all my friends were alive and threw parties at the real Y2K, but… these all feel extremely contrived. It’s as if they used AI to generate use cases for their AI tool because they weren’t really sure what it’s for…

Do you ever have a project that requires research and comparison? This can automate that.

Re: Putting Gemini to Work in Chrome

#56

Post by coffeefirst »

xnx wrote: post #55
coffeefirst wrote: post #49

Earlier quoted context omitted.

Maybe I’m a curmudgeon who can’t imagine throwing an elaborate Y2K party because all my friends were alive and threw parties at the real Y2K, but… these all feel extremely contrived. It’s as if they used AI to generate use cases for their AI tool because they weren’t really sure what it’s for…

Do you ever have a project that requires research and comparison? This can automate that.

Yeah but that's what I'm already using regular AI powered search for.

I suppose by being in the browser it can private and paywalled data, so maybe that's something.

Re: Putting Gemini to Work in Chrome

#57

Post by xnx »

coffeefirst wrote: post #56
xnx wrote: post #55

Earlier quoted context omitted.

Do you ever have a project that requires research and comparison? This can automate that.

Yeah but that's what I'm already using regular AI powered search for. I suppose by being in the browser it can private and paywalled data, so maybe that's something.

Exactly. I think I'd use it for hotel price search where you usually don't get the real price until deep in the checkout process.

Re: Putting Gemini to Work in Chrome

#58

Post by walletdrainer »

cguess wrote: post #51
walletdrainer wrote: post #16

Earlier quoted context omitted.

I use AI-controlled browsers for everyday tasks like “Find me a Michelin starred restaurant in Paris with availability for 4 people at 8PM today”. Also for things like locating a product available to pick up in a nearby store, it’s crazy how often Google fails at this particular task.

I mean, if you don't care at all about cuisine, style, location etc. I guess? Searching is half the fun of something like that. Anyways I will (continue to) not touch Chrome with a 1000ft pole after this. AI is awful in almost every aspect I've ever tasked it to.

It’ll give me a list of what’s available, the searching process isn’t made any more fun by including restaurants which will be a pain in the ass to book for a given date.

Re: Putting Gemini to Work in Chrome

#59

Post by lmm »

shakna wrote: post #11
lmm wrote: post #9

Earlier quoted context omitted.

Maybe you're only using well-designed sites? Try making a booking with a Chinese airline and you'll quickly wish for an assistant to delegate it all to.

If you struggle, then an agent will probably fail.

I know exactly what to do, it's just very tedious to actually do it. Which seems like the perfect use case for an agent.

Re: Putting Gemini to Work in Chrome

#60

Post by lmm »

dzjkb wrote: post #31
lmm wrote: post #9

Earlier quoted context omitted.

Maybe you're only using well-designed sites? Try making a booking with a Chinese airline and you'll quickly wish for an assistant to delegate it all to.

funny you say that, I was literally just booking a flight with air china yesterday and the UX was 10x better than the average wizzair/ryanair experience - a clear, readable UI (with a great table comparison of prices +-3 days from the selected dates), no ads, no random services getting pushed in your face, no booking tabs automatically opening in the background

Huh. Last time I tried with them (about a year ago), and more recently trying with China Eastern, I couldn't even get it to show me a flight that I knew was flying on a given day (just at a slightly higher price than the one it would show me).
Post reply on HN