Yes but my previous OS had zram setup as well, unless PopOS was using a worse compression algorithm, zram was not the main player here. Also there is no such thing as zram for vram unless you are talking about hardware compression.

But if the LLM stays in the V-RAM or even just stays in normal RAM does it still benefit from zram? I thought that only helped when the ram was not enough.

So I’d say it is more likely the bore scheduler + better drivers.

Basically it compresses your data in the RAM. Needs a little more work form the CPU but it is still faster than swap. https://wiki.archlinux.org/title/Zram

I had zram setup on my previous OS as well and on cachy the LLM didn’t need to use it while on my old OS it did. My guess would be that the driver had a little less overhead.

I did some Benchmarks and CachyOS claims of around 15% more performance seem to be true. Unigin Heavenbenchmark , Super Tuxkart and Furmark all got improved scores compared to PopOS. Additionally Fallout 4 now runs a lot smoother which is probably due to the BORE scheduler doing something better. My local LLMs also seem to be slightly faster and for some reason now need less V-Ram.

“Tell you never wrote code before without telling me you never wrote code before”-ass answer.

No of course not. Die you even finish reading my comment? I thought made it clear that the ease of use is not the issue. The lack of creativity is. Using Photoshop still requires you to think about what you want and how to get there. AI just gives you the output. There is no creativity involved in prompting.

When the first drawing tablets came out people loved them. Almost no one was the impression that it was “cheating”. Even with the use of AI you can still make creative projects but the creativity comes from you. Vibecoding or using image-gen does not involve creative thought.

I must disagree with you here. Telling the compiler what to do is not like prompting an LLM. I see writing code as a form of art and a big part of that is understanding the logic behind the program and the creating process. Imagine it like painting a picture. The artist/dev will undergo all the stages of drawing/coding the vision will change in the process and the outcome might be different then what was originally anticipated.

This pipeline of creating gives the project usually a better result. One could say it gives the project more soul.

With AI you are no longer the artist you are the manager requesting the result and since AI does not undergo this process of creativity the result is a soulless husk. At best only what you asked for but nothing more.

If people where complaining about AI because of its ease of use the same people would be complaining about pythons approach of humanspeech-like-code. (Not saying that there are no people that do so)

To be honest I don’t give a shit if a dev uses AI or not. As long as the code does what it is suppost to. In my personal experience AI, while still not anywhere near to capabilitys of a decent dev, can sometimes find and fix errors that I would have missed.