Natanox

Depends on the language I’d assume. The last thing I heard was that the current Codestral version is optimal for Python for example.

Yeah, same with Codestral. You have to tell it what to do very specifically, and once it gets stuck somewhere you have to move to a new session to get rid of the history junk.

Both it and ChatGPT also repeatedly told me to save binary data I wanted to store in memory as a list, with every 1024 bytes being a new entry… in form of a string (supposedly). And the worst thing is that, given the way it extracted that data later on, this unholy implementation from hell would’ve probably even worked up to a certain point.

but from my personal experience the “AMD works way better than Nvidia on Linux” mindset is no longer a thing.

Oh my god it absolutely is, and until NVK becomes the standard everywhere it will most likely stay that way. That shit breaks so often on a laptop I gonna sell soon, on my families’ computers and apparently also in computers from people in my local hackerspace. Some distros just managed to work around those drivers’ problems really well, sometimes by including them from the start of creating their own well-working packages (like Arch’s nvidia-dkms).

It’s already really good to hear you got gaming set up so quickly. A lot of people struggle with that as well either because team green (Nvidia) is involved since their drivers are utter garbage, or due to trying Linux on an older machine that doesn’t support Vulkan (which is a necessity if you want Proton to just work).

The value of getting a perfectly supported machine from a Linux vendor like System76, Tuxedo, Slimbook, StarLabs, NovaCustom etc. can’t be understated. Even more so since you also buy their customer support with it. We must not forget that, even though Linux runs on basically anything, most consumer devices are first-and-foremost Windows machines.

Ah yes, back when Windows Vista and KDE 3 were the hot shit… laggy shit, but still hot…