I've found it's pretty good for translating between steps so to speak.
Converted some bash to python relatively quickly by giving it snippets and fixing errors as it made them.
I also had success generating an ansible playbook based on my own previously written install instructions for SillyTavern and llama.cpp.
I could do both of those tasks myself, but thar would be more difficult than having a mostly correct translation and fixing some errors.
Imo this would be impossible to implement. The user can just remove whatever mark was inserted.
I'll also leave this here: https://github.com/ggerganov/llama.cpp
I've also gone down that rabbit hole and found Vivictpp pretty good. It allows you to play two videos so you can swipe between them like imgsli you mentioned.
There's a whole range measurements trying to approximate quality differences between a video source and encode. PSNR, SSIM, VMAF, MS-SSIM
All of them with some strong areas and tricks you can use to cheat them.
The EU doesn't include a bunch of countries on the continent of Europe
Then Europe is a bunch of countries wearing a bikini and lots of accessories. There's no one part that covers all of it, some accessories strongly clash with each other and you have random bracelets everywhere.
I've been playing with llama.cpp a bit for the last week and it's surprisingly workable on a recent laptop just using the CPU. It's not really hard to imagine Apple and others adding (more) AI accelerators on mobile.
Maintaining a vacuum over long distances is really fucking hard.
You'd be better served utilising existing rail infrastructure and improving that to make high speed trains possible.
You can use podman pods and generate the systemd file for the whole pod.
Nope, but it integrates very well with Podman.
Iirc that's an issue with ffmpeg. Opus itself can do that. I also stumbled upon that once.
With enough time and motivation it's probably possible, but that holds for many things.
If you're using llama.cpp, have a look at the GGUF models by TheBloke on huggingface. He puts approximate RAM required in the readme based on the quantisation level.
From personal experience I'd estimate 12G for 7B models based on how full RAM was with 16 gigs. For mixtral at least 32G.