Hacker News new | ask | show | jobs
by Hoefner 878 days ago
I hope the Chrome devs will add some features like those in Arc browser, such as summarizing content while hovering over a link and pressing Shift.
2 comments

That would be useful, but also probably quite expensive, if every chrome user use this feature?
Not if inferencing happens locally, e.g. with Gemini Nano.
Should be doable with a local model, but there might be some trade-off here. I expect it to roll out to Pixel users first where Google has a better control.
As long as laptops are still sold with 8GB of RAM, I don't see this happening.

Honestly not sure how much RAM that'd take but to me, it sounds like bloat

Desktop users are not going to be happy about a surprise local model running in the background, even a small quantized one.
So don't make it a surprise then. Besides, I'd be much less happy about my post-authenticated content being sent to a surprise cloud model...
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.

Running "smart" LLMs locally takes a lot of RAM, a lot of compute, and a lot of disk space.

It produces a considerable amount of heat unless it's run on an NPU, which basically doesn't happen on desktops at the moment.

Hot loading/unloading it can be slow even on an SSD.

Users often multitask with chrome in the background, and I think many would be very displeased to find Chrome bogging down their computer for reasons they may not be aware of.

Theoretically Google could run a very small (less than 2B?) LLM with very fast quantization, and maybe even work out how to use desktop NPUs, but that would be one heck of an engineering feat to deploy on the scale of Chrome.

Honestly that sounds extremely feasible, especially for a feature that isn't on by default. The one the parent comment references in Arc isn't on by default. Also chrome eating up system resources is already a meme and they've been working on using less by sleeping tabs.
I hope the Arc Browser team makes their Chromium based project as cross-platform as Chromium itself.
It's coming to Windows really soon! I'm not really holding my breath for Linux support though :/