[HN Gopher] Chrome's New Embedding Model: Smaller, Faster, Same ...
___________________________________________________________________
Chrome's New Embedding Model: Smaller, Faster, Same Quality
Author : kaycebasques
Score : 29 points
Date : 2025-05-13 14:39 UTC (8 hours ago)
(HTM) web link (dejan.ai)
(TXT) w3m dump (dejan.ai)
| jbellis wrote:
| TIL that Chrome ships an internal embedding model, interesting!
|
| It's a shame that it's not open source, unlikely that there's
| anything super proprietary in an embeddings model that's
| optimized to run on CPU.
|
| (I'd use it if it were released; in the meantime, MiniLM-L6-v2
| works reasonably well. https://brokk.ai/blog/brokk-under-the-
| hood)
| vessenes wrote:
| Agreed! On open source though - can't you just pull the model
| and use the weights? I confess I have no idea what the
| licensing would be for an open source-backed browser deploying
| weights, but it seems like unless you made a huge amount of
| money off it, it would be unproblematic, and even then could be
| just fine.
| darepublic wrote:
| > Yes - Chromium now ships a tiny on-device sentence-embedding
| model, but it's strictly an internal feature.
|
| What it's for "History Embeddings." Since ~M-128 the browser can
| turn every page-visit title/snippet and your search queries into
| dense vectors so it can do semantic history search and surface
| "answer" chips. The whole thing is gated behind two experiments:
|
| ^ response from chatgpt
| pants2 wrote:
| What does Chrome use embeddings for?
___________________________________________________________________
(page generated 2025-05-13 23:01 UTC)