It there's one thing I know, it's that #linux #distributions that are community driven turn out to be the most reliable. My current go to for regular users is #Fedora, because it is a solid distribution that's cutting edge and it's designed by the community.
I can't say the same for #NixOS. The amount of internal fragmentation and in fighting is too damned high, and there is possible conflict of interest that sits like an elephant in the room.
So I'm thinking... I might make a switch soon.
"You should just use #Ubuntu because it's the easiest one" - this is propaganda for #Shuttleworth and tells me you haven't tried any other distro - or that you use #Arch.
#LinuxMint is fantastic still, #Fedora is my go to recommendation, but with #uBlue and #Bazzite we see a new era of usability focused #distributions.
Add to that the fact that #snaps are a centralizes repository with no third party vendors, and you've got a #vendorlockin.
Ubuntu is the #anticonsumer distribution as a result.
@thelinuxexperiment_channel Linux Experiment had asked you, what's your favorite Distros?
You've also voted for TUXEDO OS. 
Accuracy! To counter regression dilution, a method is to add a constraint on the statistical modeling.
Regression Redress restrains bias by segregating the residual values.
My article: http://data.yt/kit/regression-redress.html
How to assess a statistical model?
How to choose between variables?
Pearson's #correlation is irrelevant if you suspect that the relationship is not a straight line.
If monotonic relationship:
"#Spearman’s rho is particularly useful for small samples where weak correlations are expected, as it can detect subtle monotonic trends." It is "widespread across disciplines where the measurement precision is not guaranteed".
"#Kendall’s Tau-b is less affected [than Spearman’s rho] by outliers in the data, making it a robust option for datasets with extreme values."
Ref: https://statisticseasily.com/kendall-tau-b-vs-spearman/
@clive
This suggests that one could detect #AI written material by comparing the word distribution to that of human writing, assuming a large enough sample. It may also be true that the word distributions from various #LLM models are different from each, in which case you now have an AI fingerprint. Comparing multiple #distributions is relatively straightforward with #statistics.
Using #CLI in #2024 feel like a constant battle between #npm and #pip. Sure, you can use your #distributions applications, or you could just fetch that library which also has a CLI script- for every operating system...
Are we winning or losing here? I'm not sure. All I know is installing npm or pip on the #server is risky business.
