Firefox introduces AI as experimental feature

Unpopular opinion, I think they're doing it right as well as it can be at least. It's completely optional and doesn't seem to be intrusive.

yeah its not google chrome level which i'm thankful about.
- I'm way more pissed about restarting my PC after an update and having Copilot installed without my permission.

Wow, great job Firefox. Thanks.

If I wanted unreliable bullshit like AI, I'd use Chrome.

Didn't want it in Opera, don't want it in Firefox. I mean they can keep trying and I'll just keep on ignoring this shit :/

This happened ages ago, didn't it? Am I missing something new?

Yeah, it did. That feature has been there at least since when Mozilla enabled "Firefox labs" section in settings by default a few months ago, and maybe even earlier than that
- TIL a month is an age.
I only saw it now, maybe it happened before on a different version.

If they do it in a privacy-preseeving way, this could help them get back market share which will generally benefit an open internet.

I really wish there was another way.
But it's gonna be very difficult when you've got Google and OpenAI up there.
Why would anybody want to have AI in their browser? It's a fucking browser.

I will say, the Le Chat provider is pretty decent. You really can use it more natural language. "Rewrite it with a better rhyme scheme" "remove the last line" and it just got it.

Why no local option though? Why no anonmysing option? Why no right click use here option for different text fields? (Like help write this as better auto complete or summarize this block of text, etc) Why no RAG using the web, why only generated text?

I don't understand the hate. It's just a sidebar for the supported LLMs. Maybe I'm misunderstanding?

Yes, I would prefer Mozilla focus on the browser, but to me, this seems like it was done in an afternoon.

It seems like common cynicism. Mozilla add this feature, as not to yield major features to other browsers. Mozilla's lets you natively have lots of different AI solutions to pick from.

Not every feature is for everyone. Not every feature is done being improved on at release.

And in spite of popular opinions, organizations don't do just one thing and then do just the next thing and the thing after that. Organizations can and do focus on and prioritize many things at the same time.

And for people who are naysaying AI at every mention, it has a lot of great and fascinating uses, and if you think otherwise, you really should try them more. I've used it plenty for work and life. It's not going away, might as well do some nice things with it.
I want my browser to be a browser. I don't want Pocket, I don't want AI, I don't want bullshit. There are plugins for that.

oh good. hurray.

I mean, if you're going to do it, where's the Ollama love?

I was disappointed there was no local option...
I don't get it, ollama is a provider no?
- A provider that can be run locally.
- I think the point is it's open source

Now add support for GPT4All and everyone is happy again.

Thing is, for your average user with no GPU and whp never thinks about RAM, running a local LLM is intimidating. But it shouldn't be. Any system with an integrated GPU, and the more RAM the better, can run simple models locally.

The not so dirty secret is that ChatGPT 3 vs 4 isn't that big a difference, and neither are leaps and bounds ahead of the publically available models for about 99% of tasks. For that 1% people will ooh and aah over it, but 99% of use cases are only seeing marginal gains on 4o.

And the simplified models that run "only" 95% as well? They can use 90% fewer resources give pretty much identical answers outside of hyperspecific use cases.

Running a a "smol" model as some are called, gets you all the bang for none of the buck, and your data stays on your system and never leaves.

I've been yelling from the rooftops to some stupid corporate types that once the model is trained, it's trained. Unless you are training models yourself, there is no need for the massive AI clusters, just for the model. Run it local on your hardware at a fraction of the cost.

Idk I noticed pretty significant differences between models of various sizes. I mean there are lots of metrics on this

https://www.vellum.ai/llm-leaderboard
There's the tragedy with this new feature: they fast-tracked this past more popular requests, sticking it into Release Firefox.

But they only rushed the part that connects to third parties. There was also a "localhost" option which was originally alongside the Big Five corporate offerings, but Mozilla ultimately decided to bury that one inside of the about:config settings.
- I'm guessing that the reason (and a good one at that) is that simply having an option to connect to a local chatbot leads to just confused users because they also need the actual chatbot running on their system. If you can set up that, then you can certainly toggle a simple switch in about:config to show the option.
Can you point me to some resources to running smol llm?

My use case prob just to help "typing" miscellaneous idea I have or check for my grammatical error, in english.

Thanks, in advance.
- Here you go: Review of SmolVLM https://www.marktechpost.com/2024/11/26/hugging-face-releases-smolvlm-a-2b-parameter-vision-language-model-for-on-device-inference/
  
  Model itself: https://huggingface.co/spaces/HuggingFaceTB/SmolVLM
  
  And you can use Ollama to run it locally, and Open WebUI to access it in browser.
- https://ollama.com/
Last time I tried using a local llm (about a year ago) it generated only a couple words per second and the answers were barely relevant. Also I don't see how a local llm can fulfill the glorified search engine role that people use llms for.
- Try again. Simplified models take the large ones and pare them down in terms of memory requirements, and can be run off the CPU even. The "smol" model I mentioned is real, and hyperfast.
  
  Llama 3.2 is pretty solid as well.
- They're fast and high quality now. ChatGPT is the best, but local llms are great, even with 10gb of vram.

Thanks for nothing, Mozilla.

They should raise the ceo's pay some more to celebrate.
- And fire a few employees just cause.

why a fucking chatbot? translate a page better for me you fucking losers, all the translation options suck for privacy outside of specifically trained local AIs. this is the BEST use case for a small local LLM yet mozilla with all its brains and resources couldnt rub two neurons together for this.

or they could do character prediction on your typing to make typing faster. just some legit examples, why waste resources to build a chat ai into my browser when i can just open a website???

Perhaps Mozilla’s biggest "failure" is just communication...

Firefox actually has this now.

For a second I thought it said "experimental failure". Would be more accurate, I think.

That was there before 133, don’t remember the exact release that added it.

I wish I had telemetry on such features.

I really doubt a significant number of people use AI chatbots often enough that having it in a dedicated sidebar is worth it.

I think nobody uses AI Chatbots, unless you're forced to do it. They're utter shit.
I've never had the urge to use a chat bot personally, but I'm pretty sure I'm in the minority. Lots of people use these things all the time for so much stuff we probably wouldn't even consider.

I've worked with a few people that all but rely on these things to produce any creative work they have to do.

Maybe we run in different circles but I think a lot of people don't even talk about how they're using it.
I wish I had telemetry

I'm sure they do as Mozilla is an ad company
- This is apparently either not widely known or some people just like to shoot the messenger.
  
  jwz, Jun.: Mozilla is an advertising company now
  
  jwz, Oct.: Mozilla's CEO doubles down on them being an advertising company now
  
  Mozilla support: Share data with Mozilla to help improve Firefox
  
  Firefox documentation: Telemetry

They better not decide to enable it by default.

it's not enabled by default ... it's opt out by default
- I think that means that it's opt-in.
- if third-party accounts are needed, it'll have to stay that way.

https://support.mozilla.org/en-US/kb/ai-chatbot

Note that you need an account to use one of these supported systems. HuggingChat allows for a few connections as a gues before cutting the access; basically a trial version, so you have to create an account.

as someone who's never dabbled with ai bots, what does this feature do? is it only to query for information like a web search?

It is a sidebar that sends a query from your browser directly to a server run by a giant corporation like Google or OpenAI, consumes an excessive amount of carbon/water, then sends a response back to you that may or may not be true (because AI is incapable of doing anything but generating what it thinks you want to see).

Not only is it unethical in my opinion, it's also ridiculously rudimentary...
- It gives you many options on what to use, you can use Llama which is offline. Needs to be enabled though about:config > browser.ml.chat.hideLocalhost.
It just adds ChatGPT or similar to your sidebar. Chatbots can do a lot of things, they are mostly good for information research and technical help, although they have serious flaws like hallucinating false information sometimes
From the description in the UI, it does sound like it. Theoretically, a chatbot could be created where you can ask questions about the webpage you have currently opened, so if you don't want to read a long article, for example. I guess, you could probably just throw a link into an existing chatbot either way, but yeah, direct integration might be convenient either way.

Well, or a chatbot could be created, which has access to your browser history, bookmarks and tabs, so you can ask it when you last saw certain information. However, you'd need a locally running chatbot for that, which makes it more difficult to implement.
good question

Are any of these open source or trustworthy?

There are no open source ai models, even if they tell you that they are. HuggingFace is the closest thing to as something like open source where you can download ai models to run locally without internet connection. There are applications for that. In Firefox the HuggingChat uses models from HuggingFace, but I think it is running them on a server and does not download from?

The reason why they are not open source is, because we don't know exactly on what data they are trained on. We cannot rebuild them on our own. And for trustworthy, I assume you are talking about the integration and the software using the models, right? At least it is implemented by Mozilla, so there is (to me) some sort of trust involved. Yes, even after all the bullshit I trust Mozilla.
- It's "open weights" if they are publishing the model file but nothing about its creation. There's some hypothetical security concerns with training it to give very specific outputs for certain very specific inputs but I feel like that's one of those kind of far fetched worries especially if you want to use it for chat or summarization and the comparison is getting AI output from a server API. Local is still way better.
I think Mistral is model-available (ie I'm not sure if they release training data/code but they do release model shape and weights), huggingchat definitely is open source and model-available
- ~~Sorry but HuggingChat / HuggingFace and all models on it are not open source~~ (Edit: Oh you meant the UI HuggingChat is Open Source. Yeah sorry, I was focused on the models. And there is no Open Source model from my understanding.) -> https://opensource.org/ai/open-source-ai-definition Off course opensource.org is not the only authority on what the word opensource means, but its not a bad start.
probably not

Could this replace Perplexity for (assisted free) online search?

Fuck you Mozilla

The chat isn't the point, it's needed as interface for storing your logins to summarization features

When internet is written by ai, you do need a tldr