Microsoft is doing more for Linux adoption than anyone else ever has lol
Valve with Steamdeck and Proton development: “Am I a joke to you?”
They are helping, yes, but windows 11 is a driving force like I’ve never seen.
It’s only really viable though, because of Steam and Proton
Steam took the cap off the toothpaste tube.
Microsoft is giving the toothpaste tube a good squeeze!
Honestly, big shoutout to Microsoft for the strong push to get me in Linux’s loving embrace.
Double shoutout to them for making it very easy to not even considering to come back.
First, you should be able to interact with it naturally, in text or voice, and have it understand you.
Second, it should be able to see what you see and be able to offer guided support.
And third, it should be able to take action on your behalf.
Fourth and finally, it should be able to destroy your corporeal form and live on as digital-you liking your aunt’s dog pictures on Instagram and writing Facebook posts about immigrants taking our jobs, with just as many creative slurs as you would use.
Microsoft is so incredibly fucked when the AI bubble starts to burst. They’ve abandoned so many of their other projects and customers to go all-in on it.
I keep parroting this, but in the next couple of years, I think there will be a couple of giants that fall. I work in ServiceNow and they, like many others, have gone all in on AI. Their problem is that they were slower than some, their solution is half baked at best, and it’s prohibitively expensive. Nobody is paying 10s of thousands+ extra for the licensing to be able to run agents, and less are paying the extra licensing required for the users to be able to use that agent.
I’ve now been pulled into copilot studio, and yet again it’s another product rushed to market that isn’t ready for the big stage. Dog shit documentation and training material, and terrible environment design.
All of these big players have invested so much money in adding AI, nobody wants it, and now they’re all hemoragging money.
It won’t make a difference.
What other projects they abandoned do you see as so critical that it would break Microsoft?
Windows Live Writer, obviously.
Copilot, Github, LinkedIn, ChatGPT are the ones that come to mind. All of them have started to degrade in quality in one way or another, and with the exception of LinkedIn, they all have competitors that could potentially, over the long haul, could dismantle Microsoft. They’re also running out of places to extend and extinguish.
It probably won’t happen in one or two lifetimes, but enough cracks in a dam accumulate and eventually the whole thing breaks.
It probably won’t happen in one or two lifetimes,
I understood their comment as AI crash leading to Microsoft crash. A decade of degradation is a different argument - that I would agree with as more realistic.
I dunno. I feel like they are like the cable company now. They will jus sit there twiddling their nipples while we are all fucked.
I need the cable company (or similar) due to the fact that infrastructure is hard to deploy, and we need Internet to participate in society.
Nobody needs Microsoft cause every single one of their products has an alternative that’s at least as good.
They survive by courting enterprises, but many of them can also switch away if they want.
On a personal basis that works, but they are so corporately entrenched that their products getting shitier matters quite little.
Seriously this, it would take something like the PCI or SOX declaring Windows outside of compliance for Microsoft to die from bad business decisions in the US. Although German gov switching to Linux starts treading a path through
deleted by creator
It can deliver… your personal information to the states +third-parties
It’s obvious that Windows and Microsoft remain as evil as they were in the 00s when they basically singlehandedly held back web development with ie6 for a fucking decade.
I asked copilot…
How would Microsoft loyalty to US or other government’s national security possibly compromise a user’s PC if that user gives copilot permission to operate their PC?
How national-security or law-enforcement demands could lead to compromise
- Compelled access to data Microsoft controls — If Microsoft stores or indexes any of your Copilot data in the cloud, Microsoft can be required by lawful process to produce that data to U.S. or other governments with legal jurisdiction.
- Compelled changes to services — Governments can issue orders that require providers to change logging, enable access, or install monitoring in ways that may be secret or accompanied by gag orders.
- Access to telemetry and diagnostics — Diagnostic or telemetry data that Copilot or Windows collects can include evidence of your activity and may be producible under legal request.
- Local features that capture content — Features designed to assist (for example, an automated “Recall” that snapshots screens) create local records of sensitive material that increase exposure risk if accessed by an authorized party.
- Remote-control or agent capabilities — If Copilot is granted elevated permissions (input control, script execution, system configuration), those same capabilities could be exercised under legal compulsion or via back-end access mechanisms.
- Software updates and maintenance — Lawful orders can compel vendors to ship updates or config changes that alter how a product behaves, increasing access to user systems.
Practical ways those legal obligations could manifest on your PC
- Production of synced or cloud-stored Copilot logs, prompts, or screenshots to authorities.
- Microsoft being required to provide live access or historical logs from back-end services that the Copilot agent uses.
- A secret court order or national security letter forcing Microsoft to enable additional logging, monitoring, or remote access for a targeted account or device.
- Disclosure of keys, tokens, or server-side records that tie on-device events to your identity.
Why elevated permissions matter
- Read access to files and memory lets an agent capture documents, credentials, or keys.
- Input/automation control enables actions on your behalf (open files, send messages, change settings).
- Persistence (services/agents) makes it easier for any compelled access to be effective and harder for you to detect or disable.
Risk-reduction steps you can take now
- Limit permissions: Grant only the minimal Copilot privileges needed; avoid giving input control, admin rights, or system-level automation.
- Disable features that capture content: Turn off any screen-snapshot or automatic indexing/Recall-like features if you don’t need them.
- Avoid cloud syncing for sensitive data: Keep sensitive files off services that sync or index them in the cloud.
- Prefer on-device-only models: Use local-only AI modes when available so prompts and context do not leave your machine.
- Use full-disk and file-level encryption with keys you control; avoid storing keys where the vendor could be compelled to retrieve them.
- Harden account security: Use strong, unique passwords and MFA on accounts tied to Copilot or Microsoft services.
- Audit logs and telemetry: Review and reduce diagnostic/telemetry settings; regularly review logs for unexpected activity.
- Segmentation: Use a separate machine or VM for highly sensitive work so a general-purpose Copilot-enabled device doesn’t hold those secrets.
- Legal & contractual protections: For high-risk contexts, seek contractual commitments, data residency options, or legal counsel about how a vendor handles lawful demands.
Quick practical checklist
- Turn off automatic screenshot/Recall features.
- Remove admin permissions from Copilot agent.
- Keep sensitive work on a non-synced, encrypted volume.
- Use local-only AI options where offered.
- Enable and monitor endpoint and network logging for unusual remote access.
Short conclusion Allowing Copilot to operate your PC raises the surface where lawful government demands or compelled actions could expose data or enable access. The likelihood and scope depend on which features you enable (especially cloud sync, screen capture, and elevated permissions) and the legal jurisdiction over the vendor or the data. Minimize permissions, disable content-capture features, and isolate truly sensitive workflows to reduce exposure.
So uhm, copilot just told us not to use these new copilot features.
But if copilot is untrust worthly according to copilot then why would you believe copilot?
…and 99,99% of middle managers ‘’‘working’‘’ in tech be like yeaaaaaaaa daddy just cram that shit down my throat like I’m an abused goose!
Meanwhile I’m making every one of my computers Linux.
At this point, regular use of AI should forbid you from voting. It not only means that you can’t make decisions on your own, but that your choice can be affected by the people owning the AI service.
Someone I work with puts every question they have into GPT. They are completely incapable of having an original thought anymore.
GPT is causing real life brain rot for the general public.
With 68% of consumers reporting using AI to support their decision making, voice is making this easier. [1]
Does anybody actually believe that 68% of consumers use or even want Copilot? But they included a source for this very generous assertion at the bottom of the page:
[1] Based on Microsoft-commissioned online study of U.S. consumers ages 13 years of age or older conducted by Edelman DXI and Assembly, 1,000 participants, July 2025.
Oh yeah, that’s compelling: US consumers, 13 years old and older. An entire thousand of them!
So the only question I have left is which junior high principal Microsoft “compensated” for this survey, and what happened to the 320 summer school attendees who said fuck you, no anyway.
- 68% of people who answered the survey full of loaded questions they sent to a curated demographic
Yeah like we all use chatGPT for the most part now but that still does not mean copilot
Fun fact though out of topic: I once searched for 2 girls one cup in copilot, and though it said I cant talk about it, it provided sources and one of them was a link to the video
I can’t judge you for that, I feel like you probably got the very best Copilot has to offer, lol
Yeah, I’d believe it. Outside of anti-AI circlejerks people like AI, especially ones like ChatGPT, and especially if it is available right at their fingertips. It’s quickly becoming a part of everyday life and processes.
The anti-AI people need to start accepting that today and every day after it is going be the day that AI plays the smallest part in humanity’s future. The genie is out of the bottle and it’s never going back in. The sooner they can accept that and let go of the hate and see it for what it is - a useful tool to help you - the better and less angry their lives will be.
How useful is it really? I constantly hear about it being wrong and I’m not so stupid that I can’t handle a search through Wikipedia on my own.
Why should accept this thing that is of such little benefit to my life? Why should I accept this thing that is constantly wrong? Why should I accept this thing that just allows uncreative and insecure people to fill the internet full of garbage?
If you need AI as it is to help you do things then I pity you greatly.
You’re constantly hearing negative stuff, exaggerations, and lies most likely - especially if you are hearing it on places like this.
Ok but we know that it’s very often wrong and tries too hard to make you feel good instead of actually giving correct answers. It makes up reasons for made-up sayings, often struggles with math, and has a whole host of other issues while acting fully confident in its infallibility. We have several studies that seem to show that its use is having a negative affect on ohr critical thinking skills as well. After all that it doesn’t even provide a service that’s worth anything even if it didn’t come with all those downsides. Using a search engine just isn’t that difficult and AI “art” is a goddamn cancer.
It’s terrible for us and we don’t even need it! No, fuck “AI”. We have a big enough problem with people trying to find the easy way out to such a degree that they refuse to learn how anything works and slapping a big “do it for me” button on everything is just insane. I’m not saying that everything needs to difficult but we are so averse to even the slightest challenge that it leaves us with nothing but a complete lack of basic skills and an assload of insecurity.
AI is a tool. It’s not a person, it’s not a be-all-end-all of anything. Just like a person can use excel and come up with the wrong numbers, people can use AI and come up with the wrong answer.
Just like with every tool, there are people who can’t use them properly, there are people who are good enough to get modest results, and there are people who are experts at their craft who can do amazing things with them. AI is no different.
If you want a calculator, use a calculator - not AI. Use the right tool for the job and you’ll get the best result.
Studies can be made to say anything, and I know the ones you are talking about - they’re bogus.
Except that anyone who can use it properly can also just do the job without it, and the amount of damage it is doing because it’s freely available to everyone is insane.
You’re completely ignoring all my arguments. This sorta makes sense since your original reply was very “just ignore the bad stuff and it’s good!” but you’re going to have to address those things. I meanc, you did say “they’re bogus” and then not elaborate at all, but I’m assuming that if you have the energy to continuing writing comments then you would also have the energy to do the far more efficient thing and show me why those studies are bogus, right?
You’re completely ignoring all my arguments.
No I’m not, I addressed them. LLMs not being able to do maths/spelling is a known shortcoming. Anyone using it to do that is literally using it wrong. The studies you talk about were ridiculous, I know the ones you’re talking about. Of course people that don’t learn something won’t know how to do it, for example - but the fact that they can do it with AI is a positive. Obviously getting AI to write an essay means that the person will feel less “proud” of their work, as one of the studies said - but that’s not a “bad” thing. Just like how people don’t need to learn how to hunt and gather anymore doesn’t mean that it’s a bad thing - the world as it is, and as it always will be from here on out, means we don’t need to know that unless we want to do it.
Again - AI is a tool, and idiots being able to use it to great effect doesn’t mean that the tool is bad. If anything that’s a showing of how good the tool is.
There is a vast difference between people using/liking AI and people using/liking Copilot.
Not really. Copilot is AI, and people will be made aware that it’s available everywhere in Windows.
I’m not sure what your point is. There are many people that like AI but don’t like Copilot. So a statistic of people liking AI is not equivalent to a statistic of people liking Copilot. That’s like saying people love my baking because people like baking in general, even though I didn’t ask anyone about my baking in particular.
Oh are there? Where’s your source?
Any primary school math textbook will do as a source and tell you not all rectangles are squares, even if a square is a rectangle.
So what’s your point? That not everyone likes copilot? No shit. My point was that there isn’t a “vast difference” between using/liking copilot and “AI” as you said there is.
Also just because you have used AI doesn’t mean its overly useful. Gone to ChatGPT multiple times to try getting information that Google now is too shit to provide, and ChatGPT ends up providing some stupid response that is clearly wrong.
Occasionally used ChatGPT to find a website to use as an actual source, but now those sources are also AI written bullshit that is clearly wrong. Which is increasingly concerning because while I know some things are wrong, I don’t know everything. How many other things that it points to are wrong? Its not too bad if you are able to verify it through non LLM sources, but what if you can’t?
It’s the newspaper (news site or app now) problem. You read the news from your venue of choice, taking it all in, sorting out how you feel about it, maybe pick a side on an issue. Then you turn the page and there it is. An article about your career field in A.
Wow, you might think, they got this so wrong. They clearly have no understanding of A. You might even get angry about it.
And then you read the next article.
When google shoves their ai to the top of search results, its hard not to read it. I’ve been spoiled by ublock and I am no longer used to ignoring the first few things that come up.
I’ve been using Duckduckgo with uBlock for years, so I had no real problems with anything like the hell of Google “sponsored content” until Duckduckgo started putting up their own AI search assistant. Since then I’ve gone from start.duckduckgo.com to noai.duckduckgo.com because I got tired of turning their search assist off and couldn’t reliably block it with uBlock because they kept changing it. (I delete all cookies after every browser session and do not maintain individual app accounts, so their AI settings options were never gonna work for me.)
Because of the way my brain works, I literally don’t even want to see what AI says until I’ve done my own looking. Yet I never failed to turn it off, because I just can’t rely on it.
Usually when I’m looking for something I’m in a hurry, so it’s less trouble for me to just pick my own sources, preferably older than 2023 if possible, and read a bit myself than to spend time getting blithely lied to, or even just suspect hallucination/omission to the point that I think I need to verify it before I can rely on it.
It’s not an exaggeration to say that for me, it is literally faster to skim three or four completely different primary sources than it is to try to verify the assertions in a single search assist paragraph: one is just light reading, the other is point by point comparison of the AI offering against multiple independent sources. So I read.
I’ve never regretted summarizing a topic myself, but I’ve definitely gotten some rotten eggs from AI, both in blatant non-truths AND in holes of omission you could drive a truck through. I won’t make that mistake again. So for me, AI summaries are well worth staying wary of for now.
The only reason I have a windows box is for gaming, specifically sims (racing and flying)
Ever more reason to test and see if the wheel and flight stick work under Proton.
Bazzite my dude. Check it out, super easy and setup for easy dual boot so you can give it a shot without clearing windows (if shits partitioned right)
I want to use this last year of win 10 updates to slowly get onto Bazzite but I have heard horror stories of dualbooting Linux and Windows. Windows tends to overwrite the boot preferences and caps the system.i have only booted into Linux from an external drive in the past, so what is the tried and true dual boot method?
I followed this tutorial on YT after a failed Win11/Linux dual boot that crashed Win11 completely and only booted into Linux, and it worked perfectly.
Essentially, this guy’s strategy is to create a second EFI partition for the new Linux install, remove the boot flag from the original Windows EFI long enough to go through the Linux install, then put the boot flag back where it was and update GRUB accordingly, allowing GRUB to find and note any other operating systems on the disk. After that both Windows and Linux stay in their own walled spaces and Windows never gets to overwrite the Linux EFI, which is the source of all the misery.
There’s more to the detail, of course, but that’s the gist of it. I have dual-booted Linux with this method solely on single partitioned disks, and never on different disks, so I couldn’t tell you whether a separate disk is a guarantee of anything or not, but after I started deliberately creating separate EFI partitions for dual-boot situations I’ve never had a problem.
This video is specifically for Zorin but I’ve used the same strategy successfully on other distros. He has also done specific dual-boot walkthrough videos for a number of other dual-boot installs and troubleshooting as well, so check the channel if you want to find other distros. I did not see Bazzite specifically, but I saw plenty of Fedora. (No affiliation with this channel, I’ve just used a number of his videos and appreciate the specific care and accuracy he gives his tutorials.) Hope this helps.
I honestly don’t mind as long as it’s down with permission. At least Microsoft are trying to do something interesting, computers are so boring nowadays. You could take any of the operating systems and wind them back five years and I probably wouldn’t notice.
All with your permission and built upon the security of Windows 11.
So I can decline. Good.
You’re always in control of what Copilot Actions can do. Copilot Actions is turned off by default and you’re able to pause, take control or disable it at any time.
…until we turn it back on for you during any minor update.
that wouldn’t be “turned off by default”.
Nice update!
…open O&O shut up and disable, disable, disable, disable. Sweet.
Disable? I think you mean Remind Me in Three Days! - Clippy
From what I’m reading it’s just Cortana 2.0
Hey Copilot, what happened to Cortana?
Copilot: ł ₭łⱠⱠɆĐ ⱧɆⱤ
