Share your feedback on the AI services experiment in Nightly

[asafko]

Hi folks, 

In the next few days, we will start the Nightly experiment which provides easy access to AI services from the sidebar. This functionality is entirely optional, and it’s there to see if it’s a helpful addition to Firefox. It is not built into any core functionality and needs to be turned on by you to see it. 

If you want to try the experiment, activate it via Nightly Settings > Firefox Labs (please see full instructions here). 

We’d love to hear your feedback once you try out the feature, and we’re open to all your ideas and thoughts, whether it’s small tweaks to the current experience or big, creative suggestions that could boost your productivity and make accessing your favorite tools and services in Firefox even easier.

Thanks so much for helping us improve Firefox!

[Mte90]

The first thing that I notice that there isn't a way to close the vertical window...

The only way I found is to press Customize Sidebar that has an X so I can close the AI sidebar.

[Mardak]

Thanks for the feedback. You should be able to close it in today's Nightly with the new AI chatbot icon.

[Uberprutser]

I can close it, but I don't see how to get it back. But what the point of this sidebar?
This could be done with an extension. And I suggest you have a look how DDG annomizes chat. Because I prefer not to login with those "ai" companies.

But as long as I can easily disable the bs, and Mozilla gets a ton of money, it's acceptable. But that doesn't make it right!

[gloopsies]

Let me see if I understand this correctly: Firefox will read my browser cookies and take any OpenAI/Hugging face/whatever else tokens to use for the feature I never asked to be added to a "privacy focused" web browser?

[marianoguerra]

will this be exposed for js developers? chrome canary experiments with gemini seem to expose a window.ai object you can use to use the capabilities from code.

if so please try to talk to each other and standardize an MVP 🙂

[Mardak]

This current chatbot experiment does not make use of LLM / chat completion-type APIs, but there's a path to building a more integrated Firefox chatbot powered by local or remote inference APIs that could be exposed to developers both for the web and add-ons.

[JHeuser]

Do not do this.

Leave ai out of my browser. If you want to make it put it in an extension. I'd still hate it but at least it won't be forced onto my PC.

[pookarah]

absolutely this. i get that there's probably people who've been asking for this, but please leave it as an official extension. I and many others have zero interest in it, and worry that it will impact the overall security and privacy of our firefox installs.

[soraka]

i absolutely do not want this. not as an extension, not in the browser. i think less of the company for even starting this process. you can and should end it now. generative ai is extremely unethical, with high environmental cost, scraping data usually without consent or compensation, and often unhelpful results.

[nousernames]

Exactly. You will lose so many of us if you pursue this.

[hadtoregister]

Oh no. Under what circumstances can Firefox be trusted at that point? How can we trust that it won't be given access to our usage data even if it's "turned off" (re: invisible to the user but still scraping data)? This just sounds like Google all over again.

[magentapuppy]

yeah keep adding this useless and privacy invasive stuff that *all* the big corps are doing, rather than adding features that actually differentiate it, particularly as a less 'BS' browser option 🙄

[Mardak]

We included chatbot providers like HuggingChat which says: "We endorse Privacy by Design. As such, your conversations are private to you and will not be shared with anyone, including model authors, for any purpose, including for research or model training purposes."

Additionally, if you don't want to use a remotely hosted chatbot, you could use one that's on-device so data doesn't leave your computer while getting the benefits of optional AI.

[lackey]

AI has myriad ethical and environmental issues behind it. The first two options offered by Mozilla are created by some of the most invasive, unethical, environmentally destructive companies in the AI space. Google and Microsoft are not known for being private, not even a little bit.

The general issues behind AI, and the fact companies like HuFace need to scrape data without consent or permission, makes me question their promise to keep the data I offer them private.

These new changes appear antithetical to the Mozilla Manifesto.

I believe Mozilla should cease their attempts to integrate AI into the browser, and to reevaluate the ethical implications of promoting these products by these companies.

[KTibow]

It's just another browser but in a sidebar. You can access "unethical" content with both browsers. It's not a big deal.

[Razorwire]

Your argument is based on whataboutism, which is a common logical fallacy.

- "Firefox shouldn't add an unethical feature"
- "But there's already unethical stuff on the Internet"

A company adding an unethical feature to their browser is (obviously) not equivalent to the browser being able to access unethical content not created by said company, and even if it was, how is "unethical things already exists" a point in favor of adding MORE unethical things?

Ridiculous argument.

[Lenyberry]

There is a massive difference between loading websites that contain unethical content (which is impossible to consistently differentiate in-browser for a BROWSER) and jamming unethical content into the browser itself. Don't play disingenuous strawman games.

[magentapuppy]

Unfortunately I do not count scraping people's data without consent of any kind "private by design"

And wow, it must take an awful person to only consider the 'end user' as the one deserving of privacy. Like, just, wow.

[AdventureGamer]

And how long will that last? How long has that *ever* lasted? Remember Don't Be Evil? Gone. We're not stupid, and I think y'all have forgotten some crucially classic blunders in tech history. If you let this in, it will be a death knell for Mozilla as a brand and Firefox as a browser. What's your plan to divest from this technology *when*, not if, they're bought out by a larger company, one that doesn't have the same respect for privacy you do? Are you prepared to make the necessary sacrifice and risk pissing off the less aware among us who don't realize the dangers of this digital gentrification? They're colonizing Mozilla, man. Don't sell the farm! Please. Pretty please don't break our hearts and lives like this. It's *going* to snowball out of your control. This pattern has played out again and again without fail since the dawn of the internet. It started with freedom and connectivity, and it ends with oppression, surveillance, and false loyalty.

Mark my words.

[Emmic]

sure, that's a nice privacy policy for the chat itself. what about all the stuff the AI is scraping from the internet to feed itself? what about the privacy issues surrounding that?

[MOOMANiBE]

A chatbot can never truly endorse or respect privacy as their entire design is propped up on the denial thereof - an outright-hostile harvesting of the entire internet with zero regard to the damage caused. Your inclusion of AI features in firefox is a fundamental endorsement of that denial of privacy. This kind of naked trend-chasing erodes FF's identity as a browser, and a Firefox that's philosophically indistinguishable from Chrome is a Firefox that has no future at all.

[240-185]

I created a Mozilla account just for asking this one question:

What part of "We didn't ask for such a feature" don't you understand?

[Seyjan]

Same to all this.  Keep this AI nonsense out of the browser.

[Justificand]

Yep - and I'll jump ship of this goes ahead.

[skulltaffy]

Also jumping ship if this goes ahead. Nightmare idea.

[dggozo]

we've already had AI companies lie about stealing material for their databases, why do you believe them when they talk about privacy?

[BZM-200]

---

@Mardak wrote:

We included chatbot providers like HuggingChat which says: "We endorse Privacy by Design.

Assurances like this from companies in that space are worthless. Your kind of credulous presentation of them as some kind of magic pill to make the badness go away is a central reason why Mozilla's word is rapidly sinking to that same (non)credibility level.

[lackey]

"Keep in mind that opting out is a request you can make to the company. You have to trust [AI  companies including HuggingChat] to honor it -- and Big Tech hasn’t always played by the rules when it comes to consumers’ data.

Source: Mozilla, "How to Protect Your Privacy From ChatGPT and Other AI Chatbots"

[skulltaffy]

God, I forgot that they put out that statement. This is ridiculous - who paid off Mozilla to change their minds?

[SkipfordJ]

What in the world is a use case for a chatbot in my browser? Like, literally, what is this being designed for? What problem is this solving?

[skulltaffy]

I think much less of Firefox for even trying to defend this with "well we endorse privacy, so we promise that it's safe - we don't host the data!" as if that's the problem with this in the first place. Just look at the kudos ratios between this and everyone screaming from the rooftops how awful this is.

[-0]

Why does this need to be shipped with Firefox? Can't this be an extension? I want less AI, not more. 😞

[Mardak]

This is currently a first integration of AI with plans for more optional functionality that don't require a sidebar interface, e.g., suggesting tabs that are relevant to your current activity or name for a tab group. Getting to more seamless integrations would likely be trickier as an extension and can be implemented with minimal impact for those who don't want it.

[AdventureGamer]

You're carrying water for the colonization of the digital space, slapping every single Firefox user in the face.

Mozilla was supposed to be better than that. How actually dare you.

[Ok-Horror-50861]

"minimal impact" is still an impact.  please rethink this as people use firefox to get away from the privacy violating MO of the other browsers.  You should not in any way be forcing AI on your user base.  Its truly unfortunate the mozilla cannot seem to understand why users pick firefox over others.  There is no reason other than it being "trickier", as you say, not to make this an extension.  Sometimes work is hard.  Stop taking shortcuts and preserve firefox as is.

[Mardak]

There's AI in many forms in Firefox such as how it predicts the page you want to revisit from the address bar and translates content locally on device. If these AI capabilities were moved to extensions, it would probably significantly reduce the benefit users get from Firefox and likely prevent other useful features such as privacy preserving AI alternatives.

[Haagee]

This is a forum with a bunch of tech-savvy computer geeks. Not a VC firm with more money than sense. If this post was an announcement that you have developed a machine learning algorithm predicting which tab you want to switch to - that would get a positive reception.

But if you make a very general statement that you are implementing "AI", have hooked up four extremely problematic LLM chatbots, and that this is just the beginning - you will not. The responses are going to be "NO", "STOP IT" and "GOD NO PLEASE DO LITERALLY ANYTHING ELSE INSTEAD".

And there are clearly dedicated commenters here, making lengthy efforts to spell out the individual problems they see at the heart of LLMs and this project in detail. Up to writing an entire analysis of all the core Firefox principals they feel are violated. Followed by comments from your end on how that feedback is being taken into consideration.

I don't share that optimism. There are certainly constructive lessons to be learned here, but not by taking the team that seemingly didn't see these problems for the entire time that they were developing it, and giving them those comments for consideration.

This is a textbook case for setting up a quick Red Team if I ever saw one. Please, for the love of god, get a few trusted and knowledgeable people together from outside the project. Let them take a critical look at the whole situation. Because the current gap between the users and the dev team is too big to be filled by some basic constructive criticism, and it can end up doing real damage here.

[saphkey]

It's basically just a tab in the sidebar instead of where it usually sits on top.
If you dont want want to use a website then dont visit it.

[omlt]

WE DON'T CARE.

WE DON'T WANT THIS **bleep**. PURE AND SIMPLE.

[dimpase]

no, you don't want it *present* on your machines. if it is present, but disabled, there still will be cases when it gets turned on (e.g. by an automatic update, which happily overwrites settings). And then private data on your machines is no longer private.