Haha. I think there’s often a rough idea on what kind of programmer people are, judging by their opinion on these AI tools.

Have you tried arguing with your AI assistant for 2.5h straight about memory allocation, and why it can’t just take some example code from some documentation? And it keeps doing memory allocation wrong? Scold it over and over again to use linear algebra instead of trigonometric functions which won’t cut it? Have you tried connecting Claude Code to your oscilloscope and soldering iron to see what kind of mess its code produces?

I’m fairly sure there are reasons to use AI in software development. And there are also good reasons to do without AI, just use your brain and be done with it in one or two hours instead of wasting half a workday arguing and then still ending up doing it yourself 😅

I don’t think these programmers are idiots. There’s a lot of nuance to it. And it’s not easy at all to apply AI correctly so it ends up saving you time.

Good comment. The main issue is this: Back in the day I could have a quick look at the code and tell within a minute whether something was coded by a 12 year old or by some experienced programmer. Whether someone put in so much effort, I could be pretty sure they’re gonna maintain the project. Put in some love because it solves some use-case in their life and it’s going to do the same for me. Assess their skill-level in languages I’m fluent in.

These days not so much. All code quality looks pretty much the same. Could be utter garbage. Could be good software, could be maintained. Could be anything, Claude always makes it look good on a first glance. There’s also new ulterior motives why software exists. And it takes me a good amount of time and detective work to find out. And I often can’t rely on other people either, because they’re either enraged or bots and the entire arguments are full of falsehoods.

As a programmer and avid Linux user, I rely a lot on other people’s software. And the Free Software community indeed used to be super reliable. I could take libraries for my software projects. Could install everything from the Debian repo and I never had any issues. It’s mostly rock solid. There were never any nefarious things going on.

And now we added deceit to the mix. Try to keep the true nature of projects a secret. And i think that’s super unhealthy. I had a lot of trust in my supply chain. And now I’m gonna need to put in a lot of effort to keep it that way. And not fall prey to some shiny new thing which might be full of bugs and annoyances and security vulnerabilities, and gone by tomorrow once someone stops their OpenClaw… Yet the project looks like some reliable software.

And I don’t share the opinion on sandboxing. Linux doesn’t have sandboxing on the Desktop. That’s a MacOS thing. All we have is Flatpak. But you’re forcing me to install 10GB of runtimes. Pass on the distro maintainers who always had a second pair of eyes on what software does, if it had tracking or weird things in it, whether it had security vulnerabilities in the supply chain. Maintainers who also provided a coherent desktop experience to me. And now I’m gonna pull software from random people/upstreams on the internet, and trust them? Really? Isn’t that just worse in any aspect?

And I don’t think Flatpak’s permission system is even fine-granular enough. Plus how does it even help in many cases? If I want to use a password manager, it obviously needs access to my passwords. I can’t sandbox that away. So if the developers decide to steal them, there’s no sandboxing stopping them in any way. Same for all the files on my Nextcloud. So I don’t see how sandboxing is gonna help with any of that. We somehow need trust and honesty.

I mean, don’t get me wrong here. I’m not saying we need to ban AI in software development. I’m also not saying 12 year olds aren’t allowed to code. I did. And some kids do great things. That in itself isn’t the issue.

Like today, just better? It’s likely still going to power most of the servers, 70% of smartphones, a lot of the embedded devices… And maybe desktop marketshare is going to rise a bit above the current 4%.

Yeah. Maybe it’s time to adopt some new rule in the selfhosted community. Mandating disclosure. Because we got several AI coded projects in the last few days or weeks.

I just want some say in what I install on my computer. And not be fooled by someone into using their software.

I mean I know why people deliberately hide it, and say “I built …” when they didn’t. Because otherwise there’s an immediate shitstorm coming in. But deceiving people about the nature of the projects isn’t a proper solution either. And it doesn’t align well with the traditional core values of Free Software. I think a lot of value is lost if honesty (and transparency) isn’t held up anymore within our community.

Did you build it, though, or did Claude code it?

Yes. I think determinism a misunderstood concept. In computing, it means exact same input leads to always the same output. Could be a correct result or entirely wrong, though. As long as it stays the same, it’s deterministic. There’s some benefit in introducing randomness to AI. But it can be run in an entirely deterministic way as well. Just depends on the settings. (It’s called “temperature”.)

Yes. I’d also be a bit cautious with just any (LLM) AI service. You could of course copy-paste something into ChatGPT if you wanted. And order it to translate the text. From my experience, it’s kinda good at it?! Handles context and idioms and tone better than other solutions. But(!) there’s a reason why other machine translation tools don’t work like that. There’s no guarantee it won’t fabricate facts, leave out detail or decide to summarize things in some weird way, and misrepresent what you put in. Pretty much all the things we know AI chatbots do.

Things like Project Bergamot (which I like to use) are way more efficient because they’re made for one specific task. And it’s designed to closely follow the input and not do weird things. So I’d prefer these solutions over random AI usage. And they likely also used less resources in some training process. And didn’t steal as many books as some other AI companies 😅 I didn’t look it up but I bet it’s way more ethical to use. Plus it doesn’t invade my privacy.

Second this. Dealing with human language is one of the few proper reasons to use machine learning, deep learning and neural somethings. As we can’t just transcribe words one by one. That just leads to very weird results no one is able to understand. I think we had rule-based systems and fairly simplistic statistics in the early days of computing. But every sane choice you’d actually want to use, leverages some form of machine learning and “AI”. DeepL does that, Google Translate, LibreTranslate, Mozilla…

That doesn’t however mean all the products are the same. There’s some blurry lines(?) where things turn into generative AI. But I’m not aware of any usable machine translation that doesn’t use some form of AI to figure out context, grammar, idioms, sentence structure and weird things like identical words which have more than one meaning.

Definitely AI. It’s one of the two good thing Mozilla did with AI. The other one being the CommonVoice project.

Maybe try good old PowerTop? Should be available in any distribution. You could either use it in interactive mode to apply powersavings. Or use it to check whether they’re (still) active.

He doesn’t have any. He grew up in an evangelical household. Studied philosophy and law. Somehow he developed a fixation on the Antichrist, Amageddon and the Apocalypse. He doesn’t have any formal backround in bible studies, though. And some people call his lectures “amateurish talk”.

https://en.wikipedia.org/wiki/Peter_Thiel

Yeah, and I’d say it’s a bit questionable whether California even has jurisdiction over revelations from God himself.

Also, I don’t think it does networking and app stores 😄

Sloppy sloppy slop slop?

100% AI text. Not even proof-read. Or they would have noticed the last paragraph is ChatGPT talking to them, not the blog audience.

I can’t relate with that kind of thinking. I like programming. I also like to be curious, lean something, solve puzzles, build something myself. I mean sure I could let someone or something do everything for me and not participate in any process. But where’s the fun in that? And what would I even do all day if I don’t use computers anymore because they do everything themselves? Don’t read anymore because that’s already summarized and the key facts stored? Not play a videogame because it plays itself? What would be the point in doing that? Don’t humans do things, and that gives some sort of meaning to things and people?

Interesting. Thanks for the info. I’ll re-think whether I recommend it to random people around the world, then.

In Germany it’s great. I’ve been using it for many years now. But we have some good/strong hacker organizations, digital sovereignty and privacy groups, nonprofits and some generous IT companies. Maybe it’s random private individuals in other countries and they’re not as reliable.

Seems right now there’s something going wrong anyway. I don’t think the amount of “offline” servers is normal. And a good amount of them isn’t even offline, but still answer my DNS queries.

After a few “Delete junk” commits, “Broken”, “PATCH: Hope this fixes it”, and “Basic Reverse-Proxy”, it’s now at version 1.0.1-alpha.1.
Don’t know what they did to Git. But their “minor commit” touches almost the entire code in their repo. Rest of it (and the general confusion and the edgy commit messages) look to me like something done by OpenClaw.

100% wouldn’t use it.

With LDAP for example (FreeIPA, OpenLDAP and a bunch of others). There’s NIS as well. If you want it exactly like AD, try Samba.

In reality, I’d probably put the users into some more modern id and auth solution, and re-assess whether I even need some Microsoft-style directory for servers and clients. I likely have better tools available.

And the big enterprise distributions, or projects like DebianEdu will have some solution listed in their documentation which is tied in into their ecosystem.

I think the Tiers work the other way around. But I keep forgetting how DNS and recursive lookup works and I might be wrong.
I don’t think you’re supposed to query Tier 1 servers as a client. The Tier 2 servers would be what people connect to and who do the heavy lifting. The Tier 1 just do the root, authoritative stuff and their custom TLDs for the following network. So we’re not worried about where those are located.

Isn’t it a global effort? According to what I see, they list a bunch of servers in all Europe, USA, Canada, Australia, …Japan?!