[dead]
The Prompt API
71–80 of 157 posts
Re: The Prompt API
#72We use this for summarising our hack day write ups: https://remotehack.space/previous-hacks/
It's a tiny script that looks up the rss feed and uses the content to generate summaries; quite a nice fit with our static site. Sometime I'd like to extend it to ask different questions about the content.
Re: The Prompt API
#73Not long before all of the web content will be going through these AI pipelines where user might not even see original webpage.
Re: The Prompt API
#74This looks like it uses Gemini Nano under the hood. But the latest Gemma4 E2B and E4B models appear to be much better, so you'd probably be better off deploying quantized versions through an extension for now.
- Gemini Nano-1: 46% MMLU, 1.8B
- Gemini Nano-2: 56% MMLU, 3.25B
- Gemma4 E2B: 60.0% MMLU, 2.3B
- Gemma4 E4B: 69.4% MMLU, 4.5B
Sources:
- https://huggingface.co/google/gemma-4-E2B-it
- https://android-developers.googleblog.com/2024/10/gemini-nan...
Re: The Prompt API
#75Gemini Nano, unlike Gemma, is not open-weight, right? I would be interested in dumping the model weights, unless someone has done that already
Re: The Prompt API
#76I led the design effort on this API, before retiring. Here's my writeup on some of the considerations that went into it: https://domenic.me/builtin-ai-api-design/
How do you envision short term and long term target usage of it? And do you guys communicate between other browsers when doing something like this to try to settle on something common? I don't mean W3C but practically, it's a small world after all.
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.
Re: The Prompt API
#77This looks like it uses Gemini Nano under the hood. But the latest Gemma4 E2B and E4B models appear to be much better, so you'd probably be better off deploying quantized versions through an extension for now. - Gemini Nano-1: 46% MMLU, 1.8B - Gemini Nano-2: 56% MMLU, 3.25B - Gemma4 E2B: 60.0% MMLU, 2.3B - Gemma4 E4B: 69.4% MMLU, 4.5B Sources: - https://huggingface.co/google/gemma-4-E2B-it - https://android-developer…
I no longer have any inside knowledge, but from my time on this team they were very quick about getting the latest small (Google) models into Chrome. I expect that if Gemma 4 (or its equivalent Gemini Nano) isn't already in Chrome, then it will be soon.
Note that the article here was last updated 2025-09-21, and as of that time it was already on Gemini Nano 3.
Re: The Prompt API
#78Earlier quoted context omitted.
Thank You stranger! I would have assumed the size would vary based on whether your hardware supports the high-quality GPU backend (4 GB) or defaults to a smaller CPU-compatible version (3 GB) but the 22GB note on that page is really confusing. Even if it was including the model server where's the remaining 18GB going towards?
I'd imagine that the 22GB was decided through modelling various scenarios. For a start, it's not just a 4GB current model, it's 2x4GB to be able to update it without needing time when the computer is without a model, that's up to 8GB. Then it's possible the model you get will scale with the CPU/GPU/RAM available, so if you have a 12GB GPU you probably get a better model, perhaps that's a 10-11GB model? At 2x that's 2…
(Former Chrome built-in AI team member here.)
This is part of it, and also we just didn't want to use up the last of the user's disk space! It's disrespectful to use up 3 GB if the user only has 4 GB left; it's sketchy if the user only has 10 GB. At 22 GB, we felt there was more room to breathe.
One could argue that users should have more agency and transparency into these decisions, and for power users I agree... some kind of neato model management UI in chrome://settings would have been cool. But 99% of users would never see that, so I don't think it ever got built.
Re: The Prompt API
#79I’m just wondering how much more RAM and VRAM chrome will use after these changes
Re: The Prompt API
#80Earlier quoted context omitted.
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.
This is sanding the edges of off life. Its gonna make you soft
There's more to life than the Internet, social media, and anonymous trolls. This is sanding the edges off the Internet. It's gonna make you happier.