Post

Paul Kinlan
@paul.kinlan.me

@jakearchibald.com - "In Chrome when you create a LanguageModel it will either use the Google Cloud API or download a 4GB model to run locally". We don't use the Google Cloud API. If the model isn't available we will kick off a download, but the API just doesn't work without the modal locally.

Michael Warren
@michaelwarren.dev

is there a permission check on the users machine before downloading? is it possible that end users get llms downloaded to their machines without their knowledge?

0 reposts0 likes

fry69
@fry69.dev

WASM based LLM inference in the browser is possible for a while. Those often download models in that size. Any website can download up to ~10GB of data in localstorage IIRC, if enough space on disk is available. Or other blobs, like e.g. astronomical images than can easily be several GB in size.

Michael Warren
@michaelwarren.dev

i guess it’s not much different than wasm. but from what i know of google literally everything from users goes into the ad machine. i would assume prompts text would also. possibly along with training google models etc. feels like there should be a permission check around llms in general

fry69
@fry69.dev

> i would assume prompts text would also Current implementation and specs do not show any hint of this behavior. LLM inference happens locally, nothing gets sent to the could.

Firefox for Web Developers
@webdevs.firefox.com

There's no permission check, and it's downloaded without the user's knowledge. The spec has points that would allow for a permission check. But, to be fair, the web doesn't limit downloads - any page can download GBs without permission. Whether they should is another question.