Linux Marketshare on Firefox

Most Linux users disable Telemetry, so I think it's probably missing around 10%
- For the fuck of it, I asked AI to guesstimate the market share
  Based on the Mozilla Graphics Telemetry data provided, Linux accounts for 3.4% of the sampled Firefox sessions. However, this is likely an underestimation of the true Linux market share for the following reasons:
  Telemetry Opt-Out: A significant portion of users may disable telemetry for privacy reasons. It's reasonable to assume that Linux users, who often prioritize privacy and are more technically inclined, might be more likely to opt out of telemetry compared to Windows or macOS users.
  Pi-hole and Ad-blockers: Tools like Pi-hole and ad-blockers, which are also more commonly used by technically proficient users (a demographic that overlaps with Linux users), can block telemetry data from being sent.
  To guesstimate the true market share, we need to consider a correction factor to account for these missing Linux users in the telemetry data. Unfortunately, precise data on telemetry disablement rates per OS is not readily available in the telemetry data itself or through a quick search.
  However, we can make a reasoned guesstimate. Let's assume:
  Baseline Telemetry Rate: Assume that for Windows and macOS, the telemetry data is relatively representative, and a smaller percentage of users disable it.
  Higher Opt-Out on Linux: Assume a significantly higher percentage of Linux users disable or block telemetry. Let's arbitrarily assume that twice as many Linux users disable telemetry compared to the average across Windows and macOS. This is a rough guess, but it acknowledges the higher likelihood of Linux users opting out. Applying a Correction Factor (Illustrative Example): This is a simplified example for illustration. To be more accurate, we'd need real data on telemetry disablement rates.
  Assume a hypothetical "average" telemetry disablement rate across Windows/macOS: Let's say, hypothetically, 10% of Windows/macOS users disable telemetry.
  Double that for Linux: Based on our assumption, 20% of Linux users disable telemetry.
  Calculate the "visible" Linux user proportion in telemetry: If 80% of Linux users enable telemetry (100% - 20% disablement), then the 3.4% in telemetry represents 80% of the actual Linux user base within the Firefox user population.
  Extrapolate to the "true" Linux market share: To find the 100% (true) Linux market share, we can do a simple proportion: If 3.4% represents 80%, then X% represents 100%. X = (3.4% / 80%) * 100% = 4.25%
  Therefore, based on this highly simplified and assumption-based guesstimate, the true market share of Linux might be closer to 4.25%. Important Considerations:
  This is a very rough estimate. The actual percentage of users disabling telemetry on each OS is unknown without specific data from Mozilla.
  Firefox User Base vs. Overall Market Share: This telemetry data is specific to Firefox users. The overall operating system market share might be different, as Firefox usage itself might be skewed towards certain operating systems.
  "True" Market Share Definition: "Market share" itself can be defined in various ways (desktop OS, all devices, etc.). This guesstimate is within the context of desktop/laptop users who might use Firefox.
  In conclusion, while the telemetry data shows 3.4%, a more realistic guesstimate, considering telemetry disablement, could be in the range of 4% to 5%. To get a more accurate figure, one would need access to data on telemetry opt-out rates per operating system or look at alternative market share data sources that employ different methodologies (though these also have their own limitations).
  
  Why post spam?
  
  I'm not gonna be a dick about it, but you really shouldn't be asking AI (or at least not a language model, use a reasoning model) things like this and accepting what they say as fact.
  The information these models have is out of date
  The information these models give is inaccurate
  You were taught how to research in school, do the math yourself instead of killing your critical thinking skills by letting an AI do the work for you.
  
  Don't listen to the haters but it would have been nice if you collapsed this because it is very long and generalized to the point that it is pretty much an eyesore. Plus most people can ask their AI of choosing semi-random topics. I don't see what was interesting in the AI response at all. It states some blatantly obvious facts and is rather too wordy. I intentionally include into the system prompt or "personalization" about how I like things to be kept short and to not reiterate what I had posted especially if it just sounds like the "AI" is thinking out loud.

It's still wild to me how many people put up with windows
- While most people find things in windows annoying, they mostly also view using a PC altogether as a chore.
  Viewed through that lense, telling them "well you can get rid of XYZ issues by investing some time in installing Linux" is like someone coming to you and saying "you can spend a few hours working on your washing machine to make it work a little faster and make the beeps less annoying".
  You're probably not going to do it. Using a washing machine is a chore already, you don't want to spend hours tinkering with your washing machine. You don't want to think about washing machines at all. You just put up with any inconveniences, then go about thinking about stuff you actually care about.
  
  Might be tempted to view it through a housing & transportation comparison too. Someone who lives in a too-big house, drives a pickup to the office and complains about expenses and how annoying it is to sit in traffic might not be particularly interested to hear from someone who lives in a comfortable flat, rarely has to go more than 15 minutes by bike and does a lot of bike maintenance themselves, leaving a lot of time & money available for fun.
  Big houses and SUVs and pickups have their place, but investing in them because it's normal and I want to be normal is likely to lead to a lot of complaints.
  That said, Kids These Days seem to be treating phones and tablets as their default OS. There's some push in workplaces to use cheaper laptops like Chromebooks if they can get away with it, which with the rise of webapps is increasingly likely. Personally I wouldn't be very surprised if Windows users in the future can be grouped into people who need:
  something that's barely not chromeos
  something more like a desktop xbox os for gamers, and
  something that's kind of a platform for specialized native non-game apps (which may or may not be legacy stuff)
  (windows server? what's that???)
- They put up with whatever the PC comes shipped with. And they hate it. Their next computer is also gonna come with windows, cause that is what they know.
  
  I guess that's how I started out too. Then someone left an Ubuntu CD just laying around and changed my life.
- The stat likely includes a lot of machines used for work and provisioned by an employer. The company I work for allows me pretty free reign with mine in terms of installing software, but wiping the OS and replacing it is the one thing I wouldn't get away with.

i took my first step today and got a usb drive so i can live boot mint and see how it runs so i can maybe install over windows on my laptop :)
edit~ hiiiii
- I doubt any version of Linux would run worse than Windows
  
  im more concerned with things like Internet not working or drivers or w/e since it's my first time trying thats all I know the actual os would be better!

I wonder if mine would've been counted there. Even before I switched to Librewolf, Debian disables most of the telemetry.
- I don't think Debian can legally modify Firefox and still call it Firefox.
  
  Telemetry can be turned off without modifying the code. I don't know about the legality of it, maybe in the case of Firefox the other things they do are also at most build options rather than code changes. But generally distros are allowed to make changes to the packages they distribute, that is how free software works.