Current setup is pi with github-copilot sub at work - limiting self to luna-6 model. I have custom tmux + nvim + lazygit setup that allows me to quickly toggle modals and jump in and out of code / markdown files for quick review. Im limiting myself like this to get a feel for agent limitations and develop a better sense for it. I could use better models but I've found that they just hide the limitations better and it's harder to learn.