

Killing your unborn baby is still killing. If the child can grow up, live a live, see parents, have friends and laugh, then it is unethical to abort.


Killing your unborn baby is still killing. If the child can grow up, live a live, see parents, have friends and laugh, then it is unethical to abort.


For context, in case any reader is not aware: Andrew Kelley, the author of this blog post, is also the creator and main developer of language Zig. And Bun was written in Zig.


DAP uses Google Analytics 360 to measure traffic and engagement across thousands of federal government websites and apps, reporting analytics under a single federal-wide shared account. Google Analytics 360 is the paid, enterprise version of Google Analytics 4 (GA4).
- https://digital.gov/guides/dap/
DAP is what the government is using, according to the Github post / page. And it’s important and equally interesting to know what the stats on the Github page exclude to present the data: https://github.com/CodebergIsBetter/platform-share-usa-gov/blob/main/analysis/os_filter.json (I love transparency)


At least you don’t start sing. I think singing would be the worst. I’m the same BTW, minus dancing. :D Especially good music, my brain is in a different dimension when I listen to good music I can “vibe” with. (Hey don’t judge, this is the first time in my life I used the vibe word appropriate).


Synthwave is my jam. But, and this is a big Butt, I’m a person who focuses on one job and get distracted too easily. So having any music in the background will distract me. So mute is it then for me.


Oh I see what you mean. You are absolutely right. Using the device less often or mostly in offline mode will drastically reduce the chance of getting the survey.


For the survey it does not matter how often you use it or how you use it, with or without internet. If you got the survey and accepted to send the data to Valve, then you are counted in that month. Otherwise not.


Oh wait, since when do they have the Steam Deck named in the stats properly? This is quiet nice.
As for the information about how many Steam users are active each month, there was an official statement by Valve. You can find it here: https://steamcommunity.com/groups/steamworks/announcements/detail/3133946090937137591 . Given that the daily active users peak in Steam is much higher now, we can assume that the monthly active users is higher too. There are estimated to the current number of 200 million at the moment: https://www.pcguide.com/news/new-report-suggests-steam-now-has-over-200-million-users-making-it-over-50-larger-than-playstation/ Who knows.
So 0.45% of 200 million estimated would be 900,000. It could also be, that Steam Deck users don’t get the survey as often or they decide not to send. The Steam hardware survey itself is an estimation based on the “few” surveys they got. At last I would expect that sales figures are higher than monthly active users number. The hardware is getting older and older, some may have moved to an alternative handheld or even to a PC. Or they have a newer OLED version alongside the LCD now.
All things considered, under 1 million users is less than I expected.
Edit: Just removed a sentence that didn’t make sense. I don’t know what I was thinking there.
I’m already on Plasma 6.7.2. :D


It has for strings and tuples, which are immutable.
If you want your mind blown a lot more
Ehm, that’s not mind blowing at all? I think there is some misundestanding. I am not talking about Strings and Tuples alone, but a global rule for all types as being immutable by default. And it would be nice to have a way to tell ANY variable to be immutable.
Scheme does not demands immutability like Clojure, but it prefers it
I’m not sure what “prefers” means in this context; do you mean it “defaults” to? Rust in example doesn’t “demand” immutability, it just defaults to it. I had looked into Clojure for a while, but I don’t like Lisp.
Just for good measure, I think Odin and Scala are also interesting languages. Whats interesting about Scala is, it can output Java Bytecode, JavaScript and native compiled code. Odin on the other hand seems to be a mixture of C and Python, but I didn’t look any further.


I was doing Bash and Python, when a few years ago learned Rust. The const by default was mind blowing how much better it was. I wish Python had const by default too.


I use Bash, Python and Rust, BTW.


I have avoided zig for a long time because it felt weird for me.
What was or is weird about Zig in your opinion? I like that Zig is kind of just a better C, that can even compile C code without modifications.


You just describe ONE way. MIT License isn’t giving up Open Source, as all Open Source projects with MIT prove it. Also the world is not only about GPL, there are other licenses in effect that either cannot or don’t want to change. In that case a program with MIT could be used and helpful for the project. In such a case its better to have a MIT licensed Open Source library instead a proprietary library, even if the whole thing is not GPL licensed (whatever it ends up being). Not all Open Source licenses are compatible with GPL, or even proprietary licenses. So having the coreutils as MIT licensed software alongside its original GNU GPL versions are not a bad thing. It’s only a bad thing, if you want to enforce GPL code for any derivative works.
And not every project or maintainer cares if someone contributes back. In fact there are a few Open Source projects (even licensed in GPL) that does not operate on a community basis and do not accept code from others, other than a closed circle of chosen developers. Also MIT license is much easier to understand and grasp and does not require a lawyer to understand it (I read it multiple times and there are still bits I get confused or forget over time). It is also less risky for companies (or for any individual for that matter, who is not well versed in licensing and just want to license a simple program in example). Meaning if a company is afraid of using GPL and they make a mistake, everything needs to be Open Source or they could get sued. They could decide not to do partial Open Source. In that case a partial Open Source with MIT License is the better choice.


Because the license has other strengths as well. Also usually and in most cases its not even a problem. And in case of the Rust coreutils, its not like as if there was no alternative like the original coreutils. So having an alternative that can be used easier in other software where GPL is a bit problematic is not a bad thing.
And the MIT License isn’t giving up on more Open Source too. So there is an opportunity.
Sounds like an Arch user.


As said, its not less open source than before. Its just not more.


According to https://github.com/linuxmint/xed
Some of the plugins, packaged and installed with xed include, among others:
* Sort
Looks like there is already a plugin installed to sort lines. Isn’t it available in the menu “Plugins > Sort”?
Edit: According to this posting, you can also sort with F10 key? Try to highlight / select with the mouse the lines and use that key.


Also noteworthy is that Cloudflare isn’t about Desktop operating systems only. I don’t know how StatCounter operates, but they probably ignore everything that is identified as mobile and Smart TV. Cloudflare is about ANY HTTP connection / request. So its natural that these numbers are quite different, as they are different in their scope anyway.
I took your post title and body text, and asked a local Ai (on my 8gb vram lol, most of it runs on cpu and is slow) what it “thinks” of. Just for the lols. I think using an Ai to answer this question is appropriate. I did not read the answer, but I think this is only fair.
Input
I there is a user in forum asking a question.
Title: “Rebuilding a social platform – how to use an AI agent as a pair programmer, not a black box?”
Body: “”" I previously let an AI agent build an entire social media site in one day. It worked, but then it introduced a bug that neither I nor the agent could fix because I had no idea what the code did. Now I want to rebuild it. I want to use AI again, but this time as an assistant – I’ll review every change, write tests together, and keep a clear plan. Which AI tool would you recommend for this hybrid approach? How do you structure prompts to force the agent to explain before coding? Also, do you think a couple of weeks is realistic to rebuild the site that has feature parity with Lemmy and a few extra features that the AI managed to build in a single day? Should I switch to a more manual approach with the agent only for boilerplate? Any advice is appreciated. Thanks! “”"
What do you think about this?
Output
This is a classic “AI Honeymoon” story. The user experienced the initial rush of seeing a functional app appear instantly, only to hit the “Complexity Wall”—the moment where the AI-generated technical debt becomes so high that the human can no longer maintain the system.
If you are responding to this user, here is a breakdown of how to analyze their situation and the advice you should give them.
1. The Reality Check: The “Lemmy” Problem
The most concerning part of the post is the timeline: “a couple of weeks… feature parity with Lemmy.”
The verdict: This is wildly unrealistic. Lemmy is not just a “social site.” It is a federated platform using the ActivityPub protocol. It involves complex distributed systems, asynchronous messaging, complex database schemas for nesting comments, and rigorous security for federation.
2. Tool Recommendations
To move away from the “Black Box,” the user needs tools that have context of the entire codebase, not just a single chat window.
3. The “Anti-Black Box” Prompting Strategy
The user wants to know how to force the AI to explain first. They need to implement a “Design-First” workflow.
Suggested Prompting Framework: Instead of saying “Build a comment section,” they should use a multi-step prompt:
4. Manual vs. AI Balance
The user asked if they should switch to a more manual approach. Yes, but specifically for the “Glue Logic.”
Summary of Advice for the User
If I were replying to them, I would say:
- google/gemma-4-31b-qat