I built an app to play with it: https://chrome-ai-example.vercel.app/
Chrome is adding `window.ai` – a Gemini Nano AI model right inside the browser
181–190 of 194 posts
Re: Chrome is adding `window.ai` – a Gemini Nano AI model right inside the browser
#182My first impression is that this should enable approximately what Apple is doing with their AI strategy (local on-device first, then filling back to a first party API, and finally something like ChatGPT), but for web users. Having it native in the browser could be really positive for a lot of use cases depending on whether the local version can do things like RAG using locally stored data, and generate structured inf…
It definitely is a terrible idea, but it follows naturally from the "browser is an operating system" approach the industry has been taking for quite a while.
With this, Goog gets to offload AI stuff to clients, but can (and will, I guarantee) sample the interactions, calling it "telemetry" and perhaps saying it's for "safety" as opposed to being blatant Orwellian spying.
Re: Chrome is adding `window.ai` – a Gemini Nano AI model right inside the browser
#183Re: Chrome is adding `window.ai` – a Gemini Nano AI model right inside the browser
#184If this is the API that Google are going with here: const model = await window.ai.createTextSession(); const result = await model.prompt("3 names for a pet pelican"); There's a VERY obvious flaw: is there really no way to specify the model to use? Are we expecting that Gemini Nano will be the one true model, forever supported by this API baked into the world's most popular browser? Given the rate at which models are…
Let alone temperature, max tokens, system, assistant, user, functions etc.
Re: Chrome is adding `window.ai` – a Gemini Nano AI model right inside the browser
#185Earlier quoted context omitted.
Presumably something like model.includes("gemini-nano:0.4") could work?
can we make everything constant like C# does please Models.GeminiNano04 boom
That would be like making a constant for every nuget package/version tuple: unworkable because new versions and packages come out all the time.
Or making constants for every device manufacturer you can connect to via web Bluetooth.
Re: Chrome is adding `window.ai` – a Gemini Nano AI model right inside the browser
#186Earlier quoted context omitted.
So many AI applications right now are just buzzword plays like that, burning hundreds of watts and seconds of latency on features that are already solved better and cheaper with traditional programs. But lots of both stakeholders and users currently value the "magic" itself over anything practical.
> So many AI applications right now are just buzzword plays like that, burning hundreds of watts and seconds of latency on features that are already solved better and cheaper with traditional programs. Internet has been already like genAI for decades. Need a picture? Prompt in the Google Image search a few keywords. There are billions of human made images to choose from. Need to find information about something? Agai…
I disagree. Take code generation. Right now stackoverflow wins on correctness but your question may not overlap entirely with the asked question. LLMs answer your actual question but you sacrifice correctness.
So there is a tradeoff so Generative AI is more useful in many circumstances.
AI is getting more accurate with time not less. It is using less energy per byte with time too for a given quality.
Guess where things will be in 2030?
Re: Chrome is adding `window.ai` – a Gemini Nano AI model right inside the browser
#187Earlier quoted context omitted.
That’s not the point. It’s an observation of how Google’s lost its status amongst hackers. It’s well into its transition into becoming the next IBM.
It has been the "next IBM" for at least 5 years
Yes, as demonstrated by the reaction to articles like this. Started out as a few dissenters and lots of praise. Now we’re down to mostly negative comments.
Another few years and most of these won’t even make it to the front page.
Re: Chrome is adding `window.ai` – a Gemini Nano AI model right inside the browser
#188Earlier quoted context omitted.
> in a way that leverages all of the local chips Which, in a way, is similar to building a browser leveraging all of the local GPUs to do render and HW-accelerated video decoding. Is Safari on Apple Silicon better than Chrome on random Windows laptop for playing YouTube in the last 5 years? Hardly.
The video plays fine on both, yes, but the Windows laptop, generally speaking, gets hotter, and runs out of battery sooner.
If you compare a random older Windows laptop to a new or nearly new Mac, sure. But new Windows/x86 PCs have gotten pretty efficient. Here's a review showing a Meteor Lake laptop getting 15 hours of video playback on battery: https://www.anandtech.com/show/21282/intel-core-ultra-7-115h...
Re: Chrome is adding `window.ai` – a Gemini Nano AI model right inside the browser
#189test
Re: Chrome is adding `window.ai` – a Gemini Nano AI model right inside the browser
#190Earlier quoted context omitted.
1.8B/3.25B is still too much for edge devices. Ideally tens or hundreds mega would be ok. Is there an option to change the builtin Gemini Nano to other smaller models? By the way, haven't touch the lastest JS code for a while, what does this new syntax mean: "import { chromeai } " Also not get the textStream code: for await (const textPart of textStream) { result = textPart; } does result get override for each loop s…
That's just some supplemental code. The actual API is: const session = await window.ai.createTextSession() const outputText = await session.prompt(inputText) That's all there is for now (createGenericSession does the same at this time, and there are canCreateTextSession/canCreateGenericSession).
Update: there's actually quite a lot more: https://github.com/explainers-by-googlers/prompt-api