Tree Style Tabs, Sidebery, or similar are must-haves. I do try to clean up my tabs regularly, but I almost always have more open that can conveniently be displayed in a horizontal tab bar.

Vertical screen real estate is at a higher premium in general on desktop, anyway. No point in keeping my browser at the full width of my screen when most sites adamantly refuse to use the space anyway (case in point: Lemmy).

Yeah I hopped back over from Edge when the manifest v3 stuff came out, and the two main things I miss are proper profile management and vertical tabs - I’ve been using https://codeberg.org/ranmaru22/firefox-vertical-tabs to get around it currently, but having a native implementation to both issues will be a massive (and recently rare) Firefox W.

If it’s using a local model like it says I think this is fine:

We’re looking at how we can use local, on-device AI models – i.e., more private – to enhance your browsing experience further. One feature we’re starting with next quarter is AI-generated alt-text for images inserted into PDFs, which makes it more accessible to visually impaired users and people with learning disabilities.

Did you read more than just the three words naming the feature? Their use case is actually smart, and could potentially help users a lot.

The recent addition of local in-browser website translation is an awesome feature I’ve missed for many years. The only alternatives I’ve found previously were either paid or Google Translate plugins. This translation feature is an example of an AI feature they’ve added.

there are 4 things

deleted by creator

A well-implemented language model could be a huge QOL improvement. The fact that 90% of AI implementations are half-assed ChatGPT frontends does not reflect the utility of the models themselves; it only reflects the lack of vision and haste to ship of most companies.

Arc Browser has some interesting AI features, but since they’re shipping everything to OpenAI for processing, it’s a non-starter for me. It also means the developers’ interests are not aligned with my own, since they are paying by the token for API access. Mozilla is going to run local LLMs, so everything will remain private, and limited only by my own hardware and my own configuration choices. I’m down with that.

I’d love to see Firefox auto-fetch results from web searches and summarize them for me, bypassing clickbait, filler, etc. You’ve probably seen AI summary bots here on Lemmy, and I find them very helpful at cutting the crap and giving me exactly what I want, which is information in text form. That’s something that’s harder and harder to get from web sites nowadays. Never see a recipe writer’s life story again!

Don’t be ridiculous…. Now an AI powered bidet that really gets the shit off your butthole…

Yes, I mean that’s one of the points explicitly listed, no?

It’s local. You’re not sending data to their servers.

We’re looking at how we can use local, on-device AI models – i.e., more private – to enhance your browsing experience further. One feature we’re starting with next quarter is AI-generated alt-text for images inserted into PDFs, which makes it more accessible to visually impaired users and people with learning disabilities. The alt text is then processed on your device and saved locally instead of cloud services, ensuring that enhancements like these are done with your privacy in mind.

At least use the whole quote.

That’s somewhat awkward phrasing but I think the visual processing will also be done on-device. There are a few small multimodal models out there. Mozilla’s llamafile project includes multimodal support, so you can query a language model about the contents of an image.

Even just a few months ago I would have thought this was not viable, but the newer models are game-changingly good at very small sizes. Small enough to run on any decent laptop or even a phone.

Don’t use it then