I don’t know if the GUID Partition Table fuckery is better or worse than what I was originally expecting when I thought your title meant you’d replaced your filesystem with ChatGPT and just let it hallucinate files in and out of existence for you. 🫠️

Ctrl+Plus/Minus and Ctrl+Scrollwheel (on mouse) adjust the font size in Firefox on my system.

I ran a 3x3 grid configuration for a long time as well – until I finally realized I needed more than that and upgraded to a 5x3 grid! 😅️

I use the center desktop for a maximized browser window and the most important stuff is usually in a plus shape immediately adjacent to that with less important things further away.

I have nuanced opinions about AI and, personally, I don’t really care how you make your memes if they’re interesting – though I will strongly discourage you from paying anyone for AI as a service to do it…

The “in 10 seconds” bit makes it really easy to flood communities with slop though, and that’s one of a number of reasons why people push back on it. There is a lot of boring AI generated stuff out there. Repetitive, same-y content is not fun – novelty is fun. If you can figure out how to push AI to do something unusual or amusing, I say have at it… but the haters are going to hate here regardless.

We had a subculture here for a while back in 2023 or so that played with AI memes. Someone would come up with an amusing idea – like Sailor Moon as a giant insect – post an AI generated picture of it, and then people would riff off it with variations of the idea until it became stale. I think those comms are basically dead at this point – and if you tried to revive them back you might get shouted off the platform given the amount of toxicity around AI now 😔️ – but there was some genuinely entertaining stuff in there occasionally!

RTX 3080-Ti Laptop AMD Ryzen 9 6900 HX

If I understand correctly, does that mean you had two GPUs in the system? (Integrated GPU in the AMD chip + a separate NVIDIA GPU?) If so, were you maybe running on the wrong GPU? Also, did you install the NVIDIA proprietary drivers or just use the out-of-the-box open stuff? For NVIDIA usually you want the proprietary ones, and for AMD open is fine, but the kernel you’re running really matters in my experience…

Tornado-kun, no! I’m not ready to go to Oz yet! 🌪️

If you just pulled the default version of qwen3.5 from ollama’s repo you downloaded a mediocre one that only uses ~6GB.

Check ollama show qwen3.5 and see if you get something like this in the result:

  Model
    architecture        qwen35    
    parameters          9.7B      
    context length      262144    
    embedding length    4096      
    quantization        Q4_K_M 

This is the default version I got when I first tried using ollama without any experience. It worked, but it’s a heavily quantized, lower parameter version of the model – i.e. it’s pretty dumb – compared to what you can actually run on your hardware.

I started running LLMs a couple months ago on my own hardware. I have a Framework Desktop that I ordered last year and also recently picked up a refurbished 24GB AMD RX 7900 XTX which I’m doing some performance testing against. The dGPU is much better for dense models, and slightly faster for MoE if I’m willing to run them at a lower quant – but uses more power and has annoying coil whine. The Framework Desktop uses ~100W under load, is quieter, and for the MoE models already runs them fast enough for most of my needs – so most of my LLM use happens on that system still.

For software: I’m using ollama on the Framework currently, but I want to replace it with just using llama.cpp directly eventually. I’ve been using llama-cli for testing the dGPU. I wrote my own chat client to interact with ollama as well as a few other programs for specific tasks.

I’ve been using the LLMs for a mix of research (both personal and professional), entertainment, practical coding tasks (mostly debugging and brainstorming, plus a bit of UI prototyping, automatic generation of sequence diagrams for documentation, and light scripting), as well as automation of tedious tasks.

As an example of the latter, people often send me requests to prepare data sets by email but don’t specify the sources they want precisely so I have to go match the name against the real name in our archives; LLMs are great for mapping the imperfect name – with typos, missing prefixes, incorrect addition of spaces, addition/removal of hyphens, etc. – to the exact name I actually need to pull the data off disk when given a lookup table to compare against.

As far as models go, I’m mostly using various Qwen 3.6 and Gemma4 variants. I have multiple versions of each for different purposes. llmfan46’s uncensored Qwen 3.6 35B-A3B @ Q6_K (from Hugging Face) is my default model currently.

I mean, if you want to retroactively classify the PornHub jingle as “cerebral catwave”, I’m not gonna stop you… 🤔️

cerebral catwave

That really sounds like it could plausibly be some niche internet microgenre of music even if you pulled it out of your butt, so maybe they just rolled with it?

(If it isn’t one yet, someone will probably make it one now that you’ve posted this… 🙃️)

Tue 07 Apr 2026 11:25:59 AM EDT

There is a good chance that lemmy.sdf.org will return after much needed disk expansion. We ran out of space. Currently everything is preserved, we just need more disks in order to bring the site back online. Thank you for your patience.

https://lemmy.sdf.org/

Hmm. Yes. A community dedicated to Unix and Surrealism. That’d be quite a thing!

On a completely unrelated topic, it seems like the SDF lemmy needs more disks… 😏️

People have already covered most of the tools I typically use, but one I haven’t seen listed yet that is sometimes convenient is python3 -m http.server which runs a small web server that shares whatever is in the directory you launched it from. I’ve used that to download files onto my phone before when I didn’t have the right USB cables/adapters handy as well as for getting data out of VMs when I didn’t want to bother setting up something more complex.