[killianlucas]

Our goal is to build this locally— there's even some heuristics we've found (i.e clicking the same items in a row every time you visit a website) that can give really good completions without an LLM.

Chrome is even starting to ship a small Gemma model in the browser, but we haven't seen great performance from Gemma yet.

But yes, and I have the same concerns w/ this, code completions, Grammerly etc. Hopefully all these tools will follow the same trajectory (some usage with a cloud setup -> distilled into a small local setup).

[pvg]

Grammarly, LLM code assistants, etc tell you upfront that this is happening and the type of info sent over is at least somewhat constrained. 'Everything I do in the browser, to multiple internet strangers' is a much bigger hurdle, especially without clear information. I think you need to figure out some way to safely demonstrate this to (informed) users - as it is, it feels far too iffy to even try which somewhat defeats the purpose of a Show HN.