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

Chrome experimental AI features

blog.google

Post reply on HN
Print view View original

71–80 of 130 posts

Re: Chrome experimental AI features

#71

Post by worksonmine »

danielbln wrote: post #60
worksonmine wrote: post #19

Anyone else have AI fatigue yet? I haven't even tried GPT and I'm already sick of AI this LLM that.

You haven't tried what would only be called science fiction 4 years ago but are tired of it? The hype machine is grating, but do try a Gen AI model. I use it for code, for ideation, for various NLP tasks. It's at the very least moderately useful in various tasks, and extremely useful in some. edit: tone

I get what it does, I've seen demos and it is no doubt impressive, but I have no personal use and don't see the point of giving them any data. I'm not limited in my current workflow and prefer official docs over the LLM interpretation of those same docs. The real satire are all the comments on any problem asking "have you tried GPT", more annoying than the Rust community.

What do you use it for that you think would benefit me?

Re: Chrome experimental AI features

#72

Post by brucethemoose2 »

chankstein38 wrote: post #65
rockemsockem wrote: post #27

Earlier quoted context omitted.

I'm curious, why do you think that?

Because it seems like, regardless of the announcement, there will always be someone who has the most niche issue with it and manages to make assertions for an entire group of people while only really referencing their personal experience ("and all of the people they know").

I mean, I am the strongest local LLM advocate you will find. I have my GPU loaded with a model pretty much all day, for recreation and work. My job, my livelihood involves running local LLMs.

But it's intense, even with a very finicky, efficient runtime on a strong desktop. Local LLM hosting is not something you want to impose on users unless they are acutely aware of it, or unless its a full stack hardware/software platform (like the Google Pixel) where the vendor can "hide" the undesirable effects on system performance.

I think that's a reasonable generalization to make.

Re: Chrome experimental AI features

#73

Post by phillipcarter »

I really wish the first part of this article had an explicit "Here is how you get started" section. I just about missed it because it's a paragraph that links to a support article. If they want people to actually use this stuff, why not make turning it on front and center?

Re: Chrome experimental AI features

#74

Post by summerlight »

punkspider wrote: post #47
summerlight wrote: post #11

As a tab hoarder, I remember there were some attempts to implement rule-based tab organizer (using features like tab name, url, etc...) but most of them were only marginally useful for my case. I wondered if generative models make any differences here so just tried it and a bit disappointed, it's consistently returning an error with a message "Tab groups suggestions are currently unavailable". It's just launched and…

How did you use it? I'm trying with Chrome Beta but it doesn't seem to have the option to organize tabs. I looked in Experiments and it's not there either. It's updated to the latest version.

https://support.google.com/chrome/answer/14519765?visit_id=6...

AFAIK, this is geo limited to the US, at least for now.

Re: Chrome experimental AI features

#75

Post by worksonmine »

summerlight wrote: post #16
izolate wrote: post #4

The first two are seemingly of questionable utility, but the 3rd feature (Help me write) is actually quite interesting. As of late, most of my public written responses (bar HN) have had some sort of collaboration with ChatGPT, and I've often wondered about a native browser integration. For those of us who struggle with communication, this is an exciting prospect!

I see this may be a good replacement for general autofill features as well. Seemingly simple autofill tasks like filling e-mail, address, name, country etc... fields never "just works" for almost all sites since this relies on correctness of the target page implementation and devs usually never care of it. Large language models should be better on this task.

You don't need an LLM to figure out what a certain field is. It's like choosing the 18 wheeler to drive your kids to school...

Re: Chrome experimental AI features

#76

Post by butz »

Soon you won't need to browse the web at all, Chrome will do everything for you: watch youtube ads, click on sponsored links, write positive reviews for restaurants buying ads from adsense, and write negative reviews for ones not advertising with google, fight with edge which browser is the default one. On the bright side, you will be able to enjoy more time offline.

Re: Chrome experimental AI features

#77

Post by rezonant »

bane wrote: post #53
yanis_t wrote: post #32

Here are some better ideas from the top of my head: - summarise an article - find information on a given topic (free-form input text) - full voice control ("click that link", "read that article", "find this") - auto-submit a captcha

Take this tab collection, build a model or a RAG or whatever around them: - Let me chat with a bot that knows the information from the collection - Use the information to generate a summary - Let me guide it in generating a well sourced article Build a knowledge graph from the web - Trace a source of information back to the originating point to help eliminate derivative blog spam - Help moderate media bias and challe…

- Post resulting article on your spam blog

- The circle continues

Re: Chrome experimental AI features

#78

Post by mderazon »

ehsankia wrote: post #44
yanis_t wrote: post #32

Here are some better ideas from the top of my head: - summarise an article - find information on a given topic (free-form input text) - full voice control ("click that link", "read that article", "find this") - auto-submit a captcha

1. This is actually a feature on Pixel through the assistant [0], surprised it's not on Chrome itself 2. That doesn't really seem like a Chrome feature? Belongs more on Bard. 3. That seems like a Google Assistant feature too, some of that actually may work on a pixel phone, though might be nice to have on desktop too. 4. Will never happen. Google themselves have a captcha product so defeats the point. [0] https://sup…

I was excited to test it on my pixel 7 just to find out it's only available on Pixel 8. Why?....

Re: Chrome experimental AI features

#79

Post by int_19h »

izolate wrote: post #4

The first two are seemingly of questionable utility, but the 3rd feature (Help me write) is actually quite interesting. As of late, most of my public written responses (bar HN) have had some sort of collaboration with ChatGPT, and I've often wondered about a native browser integration. For those of us who struggle with communication, this is an exciting prospect!

I don't know. The screenshot that they use to showcase it makes me feel the opposite - it took a perfectly clear and concise question and dressed it up in a lot of unnecessary verbiage that the person on the other end will now have to unpack to get to the gist of it.

Or they could use an LLM to translate it back to clear and concise, I suppose. But then what is it even for?

Re: Chrome experimental AI features

#80

Post by jprete »

chankstein38 wrote: post #62
fullstop wrote: post #49

Earlier quoted context omitted.

How long until malicious pages fool this into placing themselves into, say, a banking tab group?

How would that affect the end user except they go into the banking tab group and go "Huh. This isn't a banking website" and close it?

Tab groups are a mental shortcut so you can spend less time figuring out the nature of the tab you're looking at or finding particular tabs.

If something automates their creation then there is absolutely an advantage to sites that can subvert the classification method, because users will start with the "banking site" expectation instead of no expectation at all.

Post reply on HN