

Yeah right now you have to know what’s possible and nudge the ai in the right direction to use the correct approach according to you if you want it to do things in an optimized way


Yeah right now you have to know what’s possible and nudge the ai in the right direction to use the correct approach according to you if you want it to do things in an optimized way


You are in a way correct. If you keep sending the context of the “conversation” (in the same chat) it will reinforce its previous implementation.
The way ais remember stuff is that you just give it the entire thread of context together with your new question. It’s all just text in text out.
But once you start a new conversation (meaning you don’t give any previous chat history) it’s essentially a “new” ai which didn’t know anything about your project.
This will have a new random seed and if you ask that to look for mistakes etc it will happily tell you that the last Implementation was all wrong and here’s how to fix it.
It’s like a minecraft world, same seed will get you the same map every time. So with AIs it’s the same thing ish. start a new conversation or ask a different model (gpt, Google, Claude etc) and it will do things in a new way.


If you need to refractor your program you might aswell start from the beginning


I’m just not following the mindset of “get ai to code your whole program” and then have real people maintain it? Sounds counter productive
I think you need to make your code for an Ai to maintain. Use Static code analysers like SonarQube to ensure that the code is maintainable (cognitive complexity)!and that functions are small and well defined as you write it.


Same brother


Idk. Maybe you don’t want to spend the bandwidth and power on streaming it to a bunch of randoms.


For your use case its pretty much identical.
I prefer the plex interface slightly. But id rather use open source


I don’t get this argument. Isn’t the whole point that the ai will debug and implement small changes too?


Just ask the ai to make the change?
Of course. But you have to start somewhere.
90% of users probably just need a glorified table with SUM
Proton drive on Linux


Small dick government
I just run it on my gaming tower in a container


It’s a catch 22. If you need applications to make money sure. But games. Come on.
I get a PC from my job, it has windows and that’s their choice.


Just ditch those games.not worth it


Yeah I waited till I had a new gpu, got amd.
But yeah, reinstalled all the arr* stuff I had on windows and other services as podman services, got steam, played a few games. Some Linux native. Some Proton.
Transfered all my stuff then formatted my ntfs disks did btrfs
Never felt like anything pushed back on what I wanted. Was silky smooth.
Never once had to even think about if I had drivers for my things, logitech lightning mouse, wireless headset etc


Just installed CachyOS. It just works.
Never going back


You can even schedule it within copilot
They are learning from the Saudis and UAE