Skip Navigation

InitialsDiceBearhttps://github.com/dicebear/dicebearhttps://creativecommons.org/publicdomain/zero/1.0/„Initials” (https://github.com/dicebear/dicebear) by „DiceBear”, licensed under „CC0 1.0” (https://creativecommons.org/publicdomain/zero/1.0/)A

atzanteol

@ atzanteol @sh.itjust.works

Posts
4
Comments
879
Joined
3 yr. ago

  • Self hosted Card Game platform

    Jump

  • That's a much nicer read! I'm interested in some of your Claude experiences though.

    I tested Claude heavily, and I have to be direct, it consistently fell below my quality bar. Even with strict, detailed guidelines, the code it produced was riddled with subtle issues, off-by-one errors, improper error handling, and a complete disregard for my idiomatic Go patterns.

    Which Claude model were you using? Opus 3.7 & 3.8 tend to do a very good job at things like that. It catches my off-by-one issues much better than I do... They are, however, a bit slower as you point out. But my local models on an NVidia 3070 with only 8Gig of VRAM are garbage...

    Single-letter variable names might be fine for tight loops, but when you’re generating thousands of lines of code via AI, i, j, and k become impossible to trace.

    I find that if I drop in a CLAUDE.MD some style guides that it does a good job of following them. In particular I hate the Python idiom of prepending "_" to "private" variables and functions. If I put a note in there it stops it from doing it.

    As an aside - i, j, and k for loop variables is a very old tradition going back to FORTRAN where i, j, and k were always integer variables. So i is the outer loop, j the inner loop, and k the inner-inner loop. If you have more nested loops than that you're doing it wrong...

    But if you don't like it the style hint should help.

  • Self hosted Card Game platform

    Jump

  • I'll start with the unnecessarily combative tone with your reader. Then the self-contradicting absolutes (claude sucks, but my solution is x% as good as the lowest-end claude). Then the fact that it's really just an untargeted rant against "everything" that doesn't really justify the anger.

    And you hit my pet peeve about saying "containers aren't running on bare metal" when they run "on bare metal" exactly as much as non-containerized processes. That's the point of containers.

  • Self hosted Card Game platform

    Jump

  • Wow, that was just.. an awful read.

  • Setting Up OPNsense on Proxmox: Doubts regarding NIC setup

    Jump

  • Agree - critical infrastructure should have as few dependencies as possible.

  • White House weighs ‘250 pardons for 250 years’ to mark America’s birthday: report

    Jump

  • And each pardon only cost $250,000.

  • Do you host your own AI?

    Jump

  • So - I setup that model according to the docs and gave it this prompt:

     
        
Write me a highly optimized n-queens solver in go. It should take advantage of parallelism (what little there is) and output only the solution and how long it took.

    After 10 minutes it gave me code that didn't compile.

    It took another 3 mins to fix the compile error and the output is not correct.

    As I said - LLMs on 8Gig VRAM just aren't worth it.

  • Thrust into an AI role

    Jump

  • Because they're clearly looking for a way to appear to be doing the job without having to do the job.

    There's no way this forum can help with this question without knowing a lot more about the company, what they do, what they want/need, etc.

    If they truly are looking for help from this forum of ignorant strangers then they're an idiot and should just be fired anyway.

  • AI Software Development Is Near-Impossible

    Jump

  • Easy block

  • AI Software Development Is Near-Impossible

    Jump

  • You seem to be under the impression that I care about what you think and owe you anything.

    I do not.

  • AI Software Development Is Near-Impossible

    Jump

  • If you're interested you can search, since you haven't I assume you're not.

  • Thrust into an AI role

    Jump

  • You could just quit since you clearly have no desire to succeed. Or just wait until they find out and fire you.

    As a bonus you can blame "AI" either way.

  • AI Software Development Is Near-Impossible

    Jump

  • Easy block.

  • AI Software Development Is Near-Impossible

    Jump

  • It’s funny how everyone that tries to defend the use of AI, other than deny the fact that most evidence (and common sense/basic understanding of AIs) points to the idea that it’s just negative, always avoid the subject of environment.

    It wasn't even brought up twerp.

  • AI Software Development Is Near-Impossible

    Jump

  • There are papers that are pro and con. It's a new tech - we're still figuring out how to use it. It's gotten a lot better than a year or two ago though.

    It's definitely helped me get things done a lot faster. You can point to "that one study everyone does" and tell me "no it's not" but honestly, it is.

    I'll give you an example - I had to write a small bash script to fix home directory ownership on a server because somebody borked it and some critical jobs weren't launching properly. Just something to read /etc/passwd, parse out the owner and home dir and chown-R $user $home. Dozens of user dirs so quicker to just script it.

    Time was of the essence. Claude had a script in ~6 seconds. Yeah - I could have written it - but not that fast. I validated the output and gave it a run. All's good.

    You can insult me as "not good developer" or whatever you need to do to make yourself feel better - your opinion of me is irrelevant. But these tools are pretty damn good at what they do if you use them properly. "Properly" being the key word here. They are tools not employees so you need the proper critical thinking to apply them effectively.

  • What path does data take when connecting to a domain at my address?

    Jump

  • It's called "traceroute" on Linux and Mac because there was never a 8.3 filename limitation on them.

  • Do you host your own AI?

    Jump

  • Yeah - I've been playing around more with the Qwen3-Coder-30B-A3B-Instruct MoE model and it's still quite... Meh. I've been using llama.cpp and I've tried a bunch of tuning. It works and performs well enough (15t/s) but the output is just garbage. I can do some simple coding but I'm finding I'm fighting with it more than if I just wrote the code myself. Maybe I just have standards that are too high. Claude Opus 3.7 is just in an entirely different league...

  • How my AI Agent views and maintains "our" homelab

    Jump

  • Does... It matter?

    Energy use is energy use no?

    The energy required to do inference (i.e. amount it questions and the like) is no worse than doing some gaming for a short period of time.

    That said it's probably less efficient to run locally since anthropic and openai have been getting more efficient data center hardware from nvidia compared to consumer desktop gpus.

  • All you need is PostgreSQL

    Jump

  • And Oracle if you have way too much money just kicking around.

  • Ford had to hire back former engineers to fix mistakes made by its automated systems

    Jump

  • AI is a tool not an employee.

  • Do you host your own AI?

    Jump

  • I'll check that out - speed isn't my biggest issue so much as coding performance... The qwen 3.5 model I was using can write code, but it's... Meh? Like sometimes it doesn't even compile.

    I did try tweaking llama.cpp to do some cpu offloading and it does seem to allow for much larger contexts at a modest performance loss. I'll check out larger models.