I agree with the sentiment, but you underestimate the level of engineering, coordination, design work, testing it is to do this.
It is admirable that they even have a half-decent browser, but to compete at the top you need soooo much money and motivation.
The toggle for the popup is in (as you might expect) the settings hamburger menu in the AI Panel. There's even a remove button! Lots of new things have been added to browsers over the years, and these AI features are becoming incredibly popular as more users recognize the utility (and what they actually are).
This just seems like some more anti-AI hysteria.
Or—and this happens—it "summarizes" the same text differently, depending on whether the author's name happens to fit a certain ethnicity.
However, my main reason for ditching Chrome years ago was the fact that I think a browser engine monoculture is bad for the web as a whole, especially if that engine is primarily controlled by a single corporate entity.
Manifest v3 and other Google nonsense came later, and are extra reasons to stay away from Chrome, but I still feel strongly that a good alternative needs to use a different engine.
Selecting text and having a action with a custom prompt/tool without needing a browser extension might be nice. It need not even be a llm.
https://nilsheuman.github.io/TIL/2025-04-17-custom-firefox-a...
IMHO just like many companies are obsessed with adding AI features, some users are obsessed with rejecting them. Both seem mostly senseless to me, especially when it's a local-first AI implementation.
Let's not forget the CEO who paid herself a $6.9m salary in 2022, $5.6m in 2023.
https://ftp.mozilla.org/pub/firefox/releases/
You're on your own running these in the wild; at least use a few other layers of security protection. Later versions of Firefox will not run unsigned addons unless you're running a development build, without running it from the debugger page. (Maybe someone can chime in with a workaround.)
That lack of capability prevents it from being my daily driver, even if the rest were good enough (I’m not saying it isn’t, I’m saying I have no reason to find out).
I am certain I have inadvertently pushed many people away from Firefox for that reason alone, because when they ask for me to add Firefox support for my tools, I have to tell them it’s impossible.
I have tried to talk to Firefox developers about that a few times, at open-source conferences and such, but they think AppleScript is some power-user feature and fail (refuse?) to understand power users drive adoption and create tools that regular users rely on.
I remember whenever a Firefox story was submitted on HN, multiple people commented “I want to use Firefox but it’s missing <whatever>”. Then Mozilla started doing a lot of questionable stuff (all of which they eventually abandoned) outside their core competency and even pulling distasteful marketing stunts, and at some point people started commenting even that. I presume many got tired and gave up on Firefox entirely. I almost have. I now root for them only conceptually, because browser diversity is good.
I also noticed that no matter how politely someone pointed out on HN “Firefox doesn’t fit for me because of <whatever>”, they always got downvoted. If valid polite criticism is buried, no wonder things stay the way they are.
Maybe in five years they will be useful enough that it would have been worth including these features
https://data.firefox.com/dashboard/hardware
They're really not going to be able to dedicate resources to something as bijou as AppleScript.
If you've tried chrome recently, you'll know that it's jam packed full with even more stuff you don't want. And the article lays out how to easily disable all AI in firefox (which you cant do at all in Chrome)
They don’t need to do it themselves, they could just not stifle the efforts of third-parties who do want to and have worked on it. Multiple people started on it over the years and were simply ignored by the devs.
I disagree with Mozilla here, too - but you can't cast Chrome as a magic spell. Chrome sucks ass. Google sucks ass. It's trivial to suck less ass than Google.
It doesn’t to tabs, and links that the site forces to open in a new tab often don’t work. It also doesn’t do JS well by design.
I use Firefox focus for throw away links I come across, but for everything else I need a full browser
- Change to first browser tab whose URL or title matches <whatever>.
- Close every browser tab matching <whatever>.
- Grab all your tabs and backup their URLs to a file.
- Join all tabs from all windows into a single window.
- Execute JavaScript on a page and get results back.
- Grab the URL of the current tab and open it in a different browser in a Private window.
- And many more things.
I've been fully on DDG for years but becoming slowly skeptical & looking for alternatives.
1. They're leaning heavily into "responsible AI", much like Mozilla
2. Might be just me but I feel like their algorithm became significantly worse recently. Over the years they've gone from being worse than Google in the early days to steadily improving & overtaking Google on quality (I made heavy use of !g until I started slowly realising it was no longer giving me better results). But now I feel like they've reversed & regressed again.
Anyway, the reasons are irrelevant and I’m frankly tired of explaining this to Firefox defenders. Someone asked “what about Firefox are you missing” and I responded with what it’s missing for me. Plugging your ears and coming up with excuses doesn’t move the needle. Accept it or don’t, it makes no difference. In the meantime I’ll continue being honest with my users that I would like to support Firefox but I can’t, and many of them will keep switching browsers.
Do you just need to advertise stuff among content creators these days with common sense going out of the window? It'll take them a decade to catch up without any engineering funding at the level that Apple/Google/Mozilla have.
Update: I think a much better complaint is that there's no official way to disable these features.
I found family to do a decent job of not resolving ads and crapware. Other providers are available.
I’m not a content creator and I don’t really care about Ladybird. I use Safari.
I’m just pointing out that browsers have decades of legacy cruft from mis-steps deciding what the web even should be and someone smart can carve out a path to covering 90% of use cases in 10% of the effort and code. And there are the huge organizational costs Google and others pay that a small organization doesn’t have to.
Your argument is the same as looking at a large company (say Microsoft) and saying no one can compete without trillions of dollars and tens of thousands of engineers. Ladybird has the benefit of hindsight, as well as a non-idiotic structure (I assume).
The defeatism among engineers is sad
Ask 60% of their (Chrome, Edge, Safari) userbase, and they won't even be able to tell you what their browser is called.
If you're really smart and you say "I can do it with half or a quarter of the resources with hindsight", sure I might give you the benefit of the doubt, but if you're going to claim you can do it with 0.1% of the resources in a volunteer Discord server effort, no. Not because I wouldn't be happy if that was possible, but because that's not how the world works. Linux is being able to compete with Microsoft because there are now large billion dollar companies like RedHat, Steam and others investing into the development. It takes real money and developer time.
And that's the second point, Mozilla has to make these compromises because they are one of the few companies that actually maintains an independent software project at this scale. And if any other competitor ever wants to get there, they'll need to answer these funding questions too. Even if they're ten times as clever, they'll still need tens or hundreds of millions.
I don't want anything even vaguely related to spicy autocomplete on any of my machines, and I go to great lengths to kill anything that even resembles it with fire.
Maybe they'd be in a better position if they focused their resources on building their core product? I know that's a wildly radical concept these days...
The software behind Firefox can still continue without Mozilla. It may have fewer developers due to reduced funding but I'd rather see slower development if it was moving in the right direction.
I don't see why a browser should have to support AppleScript specifically. The Chrome DevTools Protocol and WebDriver BiDi are the standard protocols for interacting with browsers programmatically. Firefox supports WebDriver BiDi. Just use any tool that supports it, or talk to it directly. Maybe AppleScript can do that, I wouldn't know.
This is nice to know but in future versions of Firefox that single config switch (browser.ml.enable) will both change names and split into multiple sub-switches, most likely appearing in different pages of about:config.
These sub-switches will then not remain consistent.
Bank on it.
What makes you think it'd happen if full-time employees at Firefox cant do it? We can poop on the leadership over at Mozilla, but there are FTEs getting paid to work on Firefox.
You cant just replace with few people running passion project on weekends, and even get the remote success Firefox has.
Browser is extremely complex. HN is underestimating how much work goes into making a browser.
It'll be a usable product, but it will be extremely extremely niche, until the dev burns out or just quit it.
I hope I'm wrong, but a browser is a XXL type project and needs proper funding (means = there should be a reason for it to exist, not altruistic as lets have an alternate because reasons ..)
You don't even need an mcp server. Claude Code can just run osascript. https://news.ycombinator.com/item?id=44492369
As a user, I do not want nor need my browser to support AppleScript. AppleScript is something that should not exist. In somewhat typical apple fashion, it's some NIH platform-specific bullshit that nobody really cares about and is only half-assed supported even on it's native platform. The only way to deter Apple from creating these sisyphus-ian pieces of software is to just stop supporting them and force their hand to use something less bespoke. Although, Apple is not the only culprit of this - nor are they even the worst about it.
If I had my way, Mantle would not exist, iMessage would not exist, and some others. We would live in a perfect utopia and then we'd all hold hands and sing Kumbaya.
Almost no one changes defaults, according to the experts
It's perverse to think about:config is doing favours for anyone except Mozilla and its business partners
Otherwise the defaults would be false, i.e., opt-in
The full-time engineers are given work to do by incompetent Mozilla management. It's the management that are driving Mozilla into the ground and setting baffling goals. Remove the management and have work based on features that users want, then you can see Firefox develop in the right direction.
As an example of how to organise this, you could have a bounty system for feature requests. Users define a feature they want to see and in negotiation with developers set acceptance criteria for when it's delivered. Users can then assign money as an incentive to complete the feature request. In this way, users can ensure they support developers to deliver the features they want to see.
> Browser is extremely complex. HN is underestimating how much work goes into making a browser.
Nobody is underestimating this. Firefox is already a mature product that can serve a wide range of user needs. What it lacks is effective leadership. I could live with slower development if the development it had was based around features that users most wanted. I don't need Firefox to support every web feature under the sun, the features it already supports is good enough for the vast majority of websites. Letting the users call the shots about it's future direction will help to guard against irrelevancy.