Huh. I update my revanced YouTube app every 6-9 months

No. I am not saying that to put man and machine in two boxes. I am saying that because it is a huge difference, and yes, a practical one.

An LLM can talk about a topic for however long you wish, but it does not know what it is talking about, it has no understanding or concept of the topic. And that shines through the instance you hit a spot where training data was lacking and it starts hallucinating. LLMs have “read” an unimaginable amount of texts on computer science, and yet as soon as I ask something that is niche, it spouts bullshit. Not it’s fault, it’s not lying; it’s just doing what it always does, putting statistically likely token after statistically liken token, only in this case, the training data was insufficient.

But it does not understand or know that either; it just keeps talking. I go “that is absolutely not right, remember that <…> is <…,>” and whether or not what I said was true, it will go "Yes, you are right! I see now, <continues to hallucinate> ".

There’s no ghost in the machine. Just fancy text prediction.

Yeah, with seniors it’s even more clear how little LMs can help.

I feel you on the AI tools being pushed thing. My company is too small to have a dedicated team for something like that, buuuut… As of last week, we’re wasting resources on an internal server hosting Deepseek on absurd hardware. Like, far more capable than our prod server.

Oh, an we pride ourselves on being soooo environmentally friendly 😊🎉

Makes me feel warm around the heart to hear that it’s not just me 🫠

Even with LMs supposedly specialising in the areas that I am knowledgable (but by no means an expert) in, it’s the same. Drill down even slightly beyond surface-level, and it’s either plain wrong, or halucinated when not immediately disprovable.

And why wouldn’t it be? These things do not possess knowledge, they possess the ability to generate texts about things we’d like them to be knowledgable in, and that is a crucial difference.

I’m a programmer as well. When ChatGPT & Co initially came out, I was pretty excited tbh and attempted to integrate it into my workflow, which kinda worked-ish? But was also a lot of me being amazed by the novelty, and forgiving of the shortcomings.

Did not take me long to phase them out again though. (And no, it’s not the models I used; I have tried again now and then with the new, supposedly perfect-for-programming models, same results). The only edgecase where they are generally useful (to me at least) are simple tasks that I have some general knowledge of (to double theck the LM’s work) but not have any interest in learning anything further than I already know. Which does occur here and there, but rarely.

For everything else programming-related, it’s flat out shit.I do not beleive they are a time saver for even moderately difficult programs. Bu the time you’ve run around in enough circles, explaining “now, this does not do what you say it does”, “that’s the same wring answer you gave me two responses ago”, “you have hallucinated that function”, and found out the framework in use dropped that general structure in version 5, you may as well do it yourself, and actually learn how to do it at the same time.

For work, I eventually found that it took me longer to describe the business logic (and do the above dance) than to just… do the work. I also have more confidence in the code, and understand it completely.

In terms of programming aids, a linter, formatter and LSP are, IMHO, a million times more useful than any LM.

LMs give the appearance of understanding, but as soon as you try to use them for anything that you actually are knowledgable in, the facade crumbles.

Even for repetitive tasks, you have to do a lot of manual checking to ensure they did not start hallucinating half way through.

Dang, oof

Might even be worth checking if https://github.com/NixOS/nixos-hardware has a straight-up fix for the issue.

Yeah :(

Thanks, but for the little C# I need to write I’ll stick with nvim :D (Yeah yeah I know)

Incidentally, when I started to learn programming, I definitely was using an IDE (I can honestly not remember which one - I was following some book which included the setup of the IDE and instructions for that IDE only).

But even back then it always bugged me that I did not know what was going on in the background. When a button did not do what the book said it would do, that would turn into frustration because I could not understand what had happened, or why something failed. Sure, part of that was just inexperience, but even today, I easily despair at GUIs.

I could for example never get started with Godot because my brain just does not connect all the checkboxes and sliders with what is happening in the background. Bevy, on the other hand, was super easy to pick up precisely because there is no GUI.

Maybe I am just weird.

(Also I do not want to discourage anyone from using GUI tools, I originally just commented to support the “Linux is dev friendly” statement)

Hm, yeah, if you have an IDE made for your language, I suppose you can get around it for most things. (But that is not Windows-specific, most of those exist for Linux as well, after all).

Still, I have (for example) not worked in any project yet that did not have some bash scripts to automate project-specific tasks. Ireonically, the only person using a full-blown IDE in my team is also an absolute crack at the CLI.

I know those are anecdotal, but I would still maintain that it is very difficult to completely get around the CLI, and frankly, I do not see the benefit of doing so. An IDE is esssentially a nice wrapper around tons of CLI tools, and being able to use and understand them can only be beneficial.

Fair, but for those there presumably is a CLI as well? And conversely, what is stopping you from using a GUI debugger onLinux?

I was more thinking along the lines: you’d be hardpressed to find a debugger that does not have a CLI

deleted by creator

Can confirm, moved to NixOS.

Same is true for Windows.

Frankly you cannot get around the command line when developing.

I recommend using Usenet for German stuff, all the private trackers I have tried in the past were… seedy.

Yes, you need to pay for access to the Usenet, but it’s worth it for German language audio IMO.

Check out scenenzbs.com, no need to pay to search there. Check if everything you need is available, though likely, it will be.

I have not had a failed download yet.

Generally I agree with everyone else, Linux Mint is great.

However, if you really want to not worry at all, you could just buy a laptop from e.g. Tuxedo or System76. They come with Linux preinstalled (I think in the case of Tuxedo at least, you even have a choice of which Linux Distro?), and are guaranteed to have no hardware “difficulties” with Linux, i.e. even if you put another distro on it, you won’t encounter driver issues.

(Those have become very rare anyways, but do put a damper on the “Firsttime Linux Experience” if you do encounter them…)

Generally I agree with everyone else, Linux Mint is great.

However, if you really want to not worry at all, you could just buy a laptop from e.g. Tuxedo or System76. They come with Linux preinstalled (I think in the case of Tuxedo at least, you even have a choice of which Linux Distro?), and are guaranteed to have no hardware “difficulties” with Linux, i.e. even if you put another distro on it, you won’t encounter driver issues.

(Those have become very rare anyways, but do put a damper on the “Firsttime Linux Experience” if you do encounter them…)

Dang that’s impressive

Or disappointing, Idk