Hacker News

I actually have built myself a personal AI agent that does this for nthe main news headlines and for a summary of my personal email (sadly I can’t run it on work email yet). It can extract any actions required from a mail and make them into tasks, and also has a killer feature - a “sort out my email” button that archives all the emails it classifies as FYI, spam, mailing list or moot (it has classifiers for this), first producing a one-pager markdown summary of the whole lot in one shot, leaving all emails marked “action required” or “Urgent”. Email summaries are deliberately dry and factual with all advertising false urgency removed.

I can manually “hold” emails so they don’t go in the “sort out my email” woodchipper. It’s been life-changing.

That is unironically exactly what I want from social media.

I want the option to engage with the substance of new developments in the world, technology, etc. without the drama. I don't want to be drawn into the drama of strangers (who could, for all I know, just be bots or ragebaiting AIs).

If I want drama, there's plenty of it on TV, or I could talk to my friends about what is going on with people I actually know.

The anti-pattern, in my mind, is logging on to engage with substantive content and to be inadvertently drawn into flamewars with strangers.

Are humans supposed to enjoy the "flavor" of diarrhea, as the result of giving every village idiot a microphone so they can spew shit from their mouths?

Sure, you might say this sort of thing is boiling flavor out of your food, but... boiling the bacteria out of what you consume isn't a bad thing.

Man, that before-after slider on the home page makes me so sad... YouTube used to just be random people sharing cool stuff, and those de-sensationalized titles really brought me back to that time for a second! Cool stuff.

For people like me had tried it in the past and found it annoying, note that it now has a 'casual' mode where it only changes the truly useless titles and leaves reasonable ones alone.

I 100% agree with this. I am certain that I cannot foresee how this would play out in reality.

Yeah, I 100% agree with the caution in this comment.

I see the merit in such a proposal. It's the linguistic equivalent to boiling the food you consume, instead of eating it raw with all the associated bad stuff.

The problem is, as you said, that this plan is unlikely to be as rosy as it's portrayed and probably has a lot of drawbacks in real life.

Interesting to think about and explore, though.

on reflection, i would appreciate average slop more than the occasional heinous slop people say when they are opinionated..

I can't speak for "you guys" anymore, as I'm retired, but from my personal perspective/recollection:

The target usage for the prompt API is anything that would benefit from the general capabilities of a language model, and can't be encompassed by the more-specific APIs for summarization/writing/rewriting. Realistic use cases currently are things like sentiment analysis, keyword extraction, etc. I have a number of ideas on how to integrate it into my current retirement project around Japanese flashcards, e.g. generating example sentences. If the small (~10 GiB) model class keeps getting smarter, the class of things possible on-device in this way gets larger and larger over time.

We definitely communicated with other browsers. There were the standing WebML Community Group meetings at the W3C every few weeks. There were async discussions like https://github.com/mozilla/standards-positions/issues/1213 and https://github.com/WebKit/standards-positions/issues/495 . (Side note, I love the contrast between Mozilla's helpful in-depth feedback and WebKit's... less helpful feedback.) There was also a bit of a debacle where the W3C Technical Architecture Group tried to give "feedback" but the feedback ended up being AI-generated slop... https://github.com/w3ctag/design-reviews/issues/1093 .

But overall, yeah, the goal with the prompt API, as with all web APIs, is to put something out there for discussion as early as possible, and get input from the broad community, especially including other browsers, to see if it's something that they are interested in collaborating on. https://www.chromium.org/blink/guidelines/web-platform-chang... (which I also wrote) goes into how the Chromium project thinks about such collaboration in general.

Thanks for the insider info! Do you know if there are any published benchmarks for Nano 3?

> With MoE models, you could fetch expert layers from the network on demand

This is a common misconception, probably due to the unfortunate naming. Expert layers are not "expert" at any particular subject, and active-size only refers to the activated layers per token. You'd still need all (or most of all) the layers for any particular query, even if some layers have a very low chance of being activated.

All in all, you'd be better off with lazy loading the entire model, at least you'd know you have the capability to run inference from then on.

The model download is lazy and cached, so it's a one-time cost presumably across all origins (I assume so since the alternative would be a trivial DoS waiting to happen).

So it's once per browser, not once per site.

You can track the download state yourself and pop whatever UI you want.

chrome://on-device-internals reports "Model Name: v3Nano Version: 2025.06.30.1229 Folder size: 4,072.13 MiB" on a random Windows machine I just checked.

> Storage: At least 22 GB of free space on the volume that contains your Chrome profile.

Doesn't sound great, but consider how much better this is than every webpage trying to load their own models.

If it turns out useful enough I'm sure browsers will just start including it as (perhaps optional?) part of installation.

Nefarous use cases. Run that on some suckers machine.

Edit: simple example is a spam bot

  > This feels like a lot of work for low reward

> How many server side prompts would realistically be useful to offload to a low end model like this?

There's a lot of ways this API could go, e.g. more powerful models eventually, or perhaps integration with cloud models. For example, I could see Google trying to default Gemini as the model for users signed into Chrome

More like "you need to sign up for our website and pay for a subscription", and I'd much rather do that if it's actually providing value. I am absolutely not going to run model locally which slowly churns out words at 5 tps while making the computer hot to touch.

that is ~9% of the total available disk space for baseline phones and laptops for a model that is not that useful.

Also much better than every website wanting its own 22 GB rather than the 22 GB being a shared resource.