I replaced my $20 ChatGPT and Claude subscriptions with local AI to cut costs, but it backfired

AI subscriptions can get expensive when you're paying for more than one service. With open-weight models becoming increasingly capable, I started wondering whether I could get similar results without paying monthly fees. Since I already had a powerful PC, running AI locally seemed like a practical way to cut costs. I decided to give it a proper try to see how far I could get without relying on paid AI services. What I discovered wasn't quite what I expected. Local AI had plenty of advantages, but replacing cloud services turned out to be more complicated than simply downloading a model and running it.