1021
this post was submitted on 10 Aug 2025
1021 points (98.3% liked)
Technology
73850 readers
4355 users here now
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related news or articles.
- Be excellent to each other!
- Mod approved content bots can post up to 10 articles per day.
- Threads asking for personal tech support may be deleted.
- Politics threads may be removed.
- No memes allowed as posts, OK to post as comments.
- Only approved bots from the list below, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
- Check for duplicates before posting, duplicates may be removed
- Accounts 7 days and younger will have their posts automatically removed.
Approved Bots
founded 2 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
According to the article, this is mainly for grouping tabs with a suggested name. Talk about backwards. Use AI to process the top websites on the Internet and create groups and/or logic to group them by keywords (cluster analysis), then save the small data structure in Firefox so it can group most websites instantly, using kilobytes of ram in the process; don't try to do this on everyone's device ffs.
Besides the heat and battery problem, this also means that the GUI is going to be non-deterministic, suggesting groups differently day-to-day based on the slight differences of input and the whims of the LLM. Burn it with fire.
Oh, so that's what the fuck it was. I was wondering why my tabs were getting grouped without any logic or reason. Impressive ability to make everything actively worse
It does seem bizarre and woefully inefficient to run this process on-the-fly locally.
I don't think the centralised approach works either. If you bake that grouping metadata of individual popular pages into Firefox you have an issue with keeping it current if page content changes. And you have a difficult trade-off between covering enough pages vs not blowing up the size too much. And the approach can't work for deep web pages, e.g. anything people can only see when logged in.
Ignoring all that: The groupings you could pre-process would be static and determined over some assumed average user behaviour, not an actual cluster of a specific users themes. You take some hardcore Warhammer 40k fan, and all his tabs on minis and painting techniques and rulebooks and fan media, and apply the static grouping then it all goes into "Warhammer". However if you ran it locally it might come up with "Painting" "Figures" "Rules" "Fanart" or whatever. It would produce a more fine grained clustering for someone who is deep into a specific niche interest, and a more coarse grained one otherwise.
So I think fundamentally it's correct to cluster locally and dynamically for a usable result. They need to make it opt-in, and efficient enough. Or better yet they could just abandon the idea because it's ultimately not that much use compared to the required inference cost.