Orbit is an LLM addon/extension for Firefox that runs on the Mistral 7B model. It can summarize a given webpage, YouTube videos and so on. You can ask it questions about stuff that’s on the page. It is very privacy friendly and does not require any account to sign up.
I personally tried it, and found it to be incredibly useful! I think this is going to be one of my long term addons along with uBlock Origin, Decentraleyes and so on. I would highly recommend checking this out!
I’m just glad it’s an add on/extension. A lot of the crap baked into browsers these days is just bloat nobody wants or uses.
The general tone in this thread seems so very different from when “Mozilla is working on AI” was first announced
Can I just trade in that LLM for the old Firefox please?
Maybe they could focus on developing a web browser instead…
Considering how google is making chrome worse every day, they could do only security updates and still be the best browser.
So mozilla is paying the server costs for this, what’s the business model?
AI
Most important part of the thread:
In it’s beta stage, Orbit is currently not open-source. This doesn’t mean it will remain this way forever. If orbit gains traction and we have the resources and funding to support an Open-Source project, I’m sure things could change.
Press X to doubt.
Has Mozilla done sometime to deserve this skepticism? They were founded on open-source and AFAIK have continued to support open-source. Mozilla is far from a perfect organization, but if this project was a success I think it would be out of character for them to keep it closed-source.
Pocket.
That’s a pretty good answer. I knew Mozilla had bought it, and were operating it as an independent subsidiary. I didn’t know they promised to open-source it over 7 years ago.
They said they’d open source Pocket and they didn’t. In fact, they’ve simply allowed it to rot and just removed features. So here I think the skepticism is warranted.
Has Mozilla done sometime to deserve this skepticism?
Yes, their “privacy friendly ad measurement” that’s opt out is a faux pas that I just can’t forgive. I used to donate to the fuckers.
It does not affect you if you use an adblocker, this feature is meant to allow websites to have ad analytics without tracking.
User JohnFen on ycombinator’s hacker news said it nicely and I’m lazy, so:
PPA means that my browser is doing the spying instead of a third party directly. That’s certainly a privacy improvement, but I don’t consider it sufficient.
“Sufficiently private” is a subjective call. I don’t want to be spied on. Whether or not there are technological “privacy preserving” features baked into it doesn’t alter that fundamental fact.
All that said, this isn’t a bad enough move to get me to stop using Firefox, as long as I can keep it disabled. It does mean that I have to view Firefox with suspicion, though. I can’t consider the browser to be my “user agent” anymore.
Well, since you copy-pasted, i will likewise share my favorite take on thr situation.
After reading about the actual feature (more), this seems like an absolutely gigantic non-issue. Like most anti-Mozilla stories end up being.
The whole thing is an experimental feature intended to replace the current privacy nightmare that is cross-site tracking cookies.
As-implemented it’s a way for advertisers to figure out things like “How many people who went to our site and purchased this product saw this ad we placed on another site?”, but done in such a way that neither the website with the ad, nor the website with the product, nor Mozilla itself knows what any one specific user was doing.
The only thing I looked for but could not find an answer on one way or the other is if Mozilla is making any sort of profit from this system. I would guess no but actually have no idea.
There are definitely things that can be said about this feature, like “Fuck ad companies, it should be off by default” (my personal take), or “It’s a pointless feature that’s doomed to failure because it’ll never provide ad companies with information as valuable as tracking cookies, so it’ll never succeed in its goal to replace tracking cookies” (also my take). But the feature itself has virtually no privacy consequences whatsoever for anybody.
I’m absolutely convinced there’s a coordinated anti-Firefox astroturfing campaign going on lately.
That feature (more) they’ve been getting all that negative press over for the past two days is an absolutely gigantic non-issue. Like most anti-Mozilla stories end up being.
The whole thing is an experimental feature intended to replace the current privacy nightmare that is cross-site tracking cookies. As-implemented it’s a way for advertisers to figure out things like “How many people who went to our site and purchased this product saw this ad we placed on another site?”, but done in such a way that neither the website with the ad, nor the website with the product, nor Mozilla itself knows what any one specific user was doing.
There are definitely things that can be said about this feature, like “Fuck ad companies, it should be off by default” (my personal take). But the feature itself has virtually no privacy consequences whatsoever for anybody, and Mozilla is at least trying to build a system that would legitimately improve the privacy situation on the internet created by companies like Google.
I don’t think that whether it has a privacy impact even matters. What matters is how it demonstrates Mozilla’s attitude towards user consent.
Firefox is sustained (biggest funder) by google who needs artificial competitions to not be labeled a monopoly.
Its still the best browser i can think off that isn’t chromium but i would recommend staying skeptical.
Eh, skepticism should be the default.
But I agree with you, nothing they’ve done is inherently bad, though they’ve done some abysmally stupid things in the way they handle them.
But I also really wish they’d stop fucking around with half-assed things like this and focus on core utilities.
What core utilities does Firefox need that it doesn’t have? Honest question. I’ve been using it over a decade and never had it fail to do something I asked it to, and I’m a little out of the loop on the web browser development news cycle beyond the recent wave of Google Bad.
Mozilla has firefox and thunderbird. They’re the two core utilities. The vpn attempt, the Mastodon server, that kind of stuff is fluff.
I may be using the wrong terminology? It was an offhand comment and that’s the word that I picked out of my head, it might mean something different to a developer, I dunno.
But Mozilla, if you ignore what Google pays them, is not exactly a high profit endeavour, and we don’t want it to be. So having what funds they have focused onto the things that matter is what I’d prefer they do. Mind you, if the vpn pulls enough in to generate funds rather than cost them, that’s great.
then why make it closed source to begin with?
Believe it or not but it requires resources to open source an internal product, especially one that may have been an experiment where some small team was able to convince leadership could become useful to the masses.
React.js at Facebook is a good example of this. It took a lot of effort to externalize and open source React, and tbh the codebase is still kind of garbage when it comes to contributions from those unfamiliar with its intricacies.
but… you dont have to accept contributions? you can just make it open source and tidy it up at the same time?
In a different world maybe, but I can already see the headlines, “Mozilla open sources lackluster AI tool”. PR is unfortunately a thing, and once you miss that initial wave of interest, you’re unlikely to grab attention later without another marketing push. Mozilla is experienced in open sourcing software, so by now they’re pretty good at knowing when to do it and when not to. In other words, it says something that they chose not to do it in this case.
Yeah, it definitly tells me something, namely that I should not use the tool.
Why would news publish articles about the code quality of the tool, instead of its functionality?
Now they have negative press about its closed source nature, which is a calculated risk they took, just to open source it soon anyway? I doubt it.
So risk someone else beating you to market? And they’ll either have the resources to make it superior, therefore making yours irrelevant, or they’ll make it inferior, which generated bad press for you
It’s provocative it gets the people going.
If you really care for an LLM, run it locally… Not sure if this does it…
Don’t want to install and maintain 10gigs of cuda stuff on my PC. Next, my mum won’t know how to do that. Her laptop is a potato. This add-on makes all of this way easier.
You don’t need CUDA, it’s actually pretty easy. You can run the Mistral 7B model this add-on is based on using GPT4All. It doesn’t require much, if any, technical knowledge.
HOLY HELL THAT’S COOL. It can do so much too!!!
I locally installed some small LLM model more than a year ago. It took up like 25 gigs or something along with all CUDA libraries n stuff. It was alright, but I figured that cloud based solutions were the best for my use case, as they were better and for free.
I had no idea that open sourced AI progressed so much in the last year. Amazing stuff!
It depends how you run it etc. You may have not been using a quantized model.
what’s the min-sys requirements for a good experience?
A midrange graphics card and 16 GB of RAM should suffice. Check their site for specifics.
You’re not generating models at this point. You don’t need that kind of hardware to run these.
Well that comes with shit ton of privacy risk. If y’all are comfortable, then it is your choice
It is very privacy friendly […]
What makes you believe that? The most information I could find about this is that it doesn’t “save your session data.” The Orbit privacy policy also seems a bit bare, and I can’t decide if that’s a good thing or not.
Either way, you’re still sending data to a third party service to process. Might be worth it for some people.
No association with any account. Therefore, no profiling.
Facebook and Google profile you with no account. Accounts aren’t required for tracking.
Probably not for me as I’m not interested in a summarizing tool, but I’m not against AI in general.
OAN, I think over time, the community will see that AI was a bubble, but in the same way that the internet was a bubble back in the day.
OAN, I think over time, the community will see that AI was a bubble, but in the same way that the internet was a bubble back in the day.
Surprised to see this opinion on Lemmy haha. Yep, totally agree with ya here!
Everyone wants a Her style personal assistant — as in one that is personal-context aware, can simplify, and generally enrich their lives (not for emotional support) — but if most people knew how unintelligent AI is, how spectacularly it fails, and how dangerous it is to integrate it into information systems and (especially) give it any ability to act … Literally nobody would want to give it access to all their data, or use it beyond an advisory role.
Perhaps I’m a luddite - but I unequivocally do not want an assistant like that. I dislike even the basic commands of google assistant. I can do the tasks better and faster than than the assistant can.
Amen to that. I’m not a busy CEO of four companies, I don’t need or want an assistant, digital or otherwise. I want to read through articles and watch videos, I can scroll/fast-forward through myself if I feel like it. And while we’re at it, I don’t really need or want personalized anything - just give me ALL the search results and I’ll sort through them myself. Luddite? Maybe, but I literally cannot think of a case where this would be useful or helpful to me…
In before is not just skips important details in its summarization, but also hallucinates its own interpretation of things into it.
Generally, don’t call it “AI”, don’t overhype it, don’t use it where it is bad in its function (like telling you “facts”), don’t shove it into everything. I bet 80+ percent of all “AI” energy consumption is wasted on completely useless and moronic tasks that have 0 value even on a personal level.
"The term “AI” has been in use since 1956 for a wide range of computer science techniques. LLMs most certainly qualify as AI. You may be thinking of the science-fiction kind of “artificial people” AI, which is a subset of AI called Artificial General Intelligence when researchers want to be specific about that kind.
I’m thinking of something that actually processes some form of “thought”, in the abstract sense. Even video game AI does that to an extend (granted, there’s various techniques depending on the game type), so the term here is actually somewhat appropriate. LLMs don’t do that at all though, they’re just word guessing based on the texts they were trained upon (while we stick with text gen here at least) and that just so happens to sound like somewhat coherent sentences that can fool someone into thinking that their computer actually talked to them. There never was any sort of thought behind that though. It functions closer to how your mobile keyboard predicts the next word you want to use in its suggestions at the top. It just tries to complete the text it was already presented with. A lot of the illusion here comes actually from the tools used to display this information in a chat like manner, but that’s just frontend foolery for the user.
I think it’s more that you’re overestimating video game AI, here. If your definition of “abstract thought” doesn’t include what LLMs do then it definitely shouldn’t include video game AI. It’s even more illusory.
Yeah but you think a lot of weird things, so that does not surprise me in the slightest.
I would agree with the other guy. A video game AI can be as simple as some if-then decision logic, and i would count that as “AI”. An LLM also makes “decisions” on what to do/say, just via a different mechanism (predictive modeling) . I would still bucket that as AI. It you count one you should count the other. Neither are truly “thinking” in the sense of an AGI.
I wasn’t talking about something like an AI in Pong. But if your definition of “AI” is conditionals such as if statements, then absolutely everything is an AI, which honestly just further muddles the meaning of that term.
Gross.
Ooh, I just tried it out and I can tell I’m going to love it - if not this specific plugin (the UI needs some work) then this general concept of a plugin.
I just popped over to Youtube and went to a ten-minute video of something or other, clicked the “summarize transcript” button, and within a few seconds I had a paragraph-long summary of what the whole video was about. There have been sooo many Youtube videos over the years that I’ve reluctantly watched with a constant “get to the point, man!” Frustration. Now I’ll know if it’s worth it.
Do you have the SponsorBlock add-on installed? Most videos have user-submitted sections that it lets your skip. Also, a highlighted part.
Hm…could be useful for those times you want to read a guide but can only find one in video form
RIGHT?!!! IT’S SO FKIN AMAZING
This is especially going to be useful for me as a student. It’s just feels like browser 2.0 at this point haha
Huh, I’ll have to check it out then. This will be especially useful for Louis Rossmann videos because he rambles and repeats himself a lot.
deleted by creator
“we have a few potential paths to follow depending on the feedback we receive. Running a truly local LLM is one that we’re researching at the moment”
In that case, fuck off with this bullshit until your research is done, that’s some feedback for you.
- I don’t think this is the proper channel for feedback.
- Rude
- Fuck you. This is an optional extension for those who want to try. Do you want the final version of a piece of free software? Then you can go lie in a ditch because hopefully it will continue to evolved for years. It’s astonishing the entitlement of some people.
- Good local LLM that can run on most hardware is a very interesting project. Usually you need at least a GPU to get it to run. The fact that is only summarizing might be because it this.
You’re right, it was rude. Sorry.
