Am I missing something: "[TUIs are] easy to automate". What am I not seeing or know about? I had to go crazy mad routes of automating TUIs with `tmux` just to get to some repeatable process.
Hmm, I'm not convinced that is the direction we want to go in. It's not like we have all the context of everything we ever learned present when making decisions. Heck, even for CPUs and GPUs we have strict hierachy of L1,L2,L3 shared, caches to larger memory units with constant management of those. Feel free to surprise me, but I believe having a similar stack for LLMs is the better way to go where we will have short-term memory (system-prompt, prompt, task), mid-term memory (session-knowledge, preferences), long-term memory (project knowledge, tech/stack insights), intuition memory (stemming from language, physics, rules). But right now we haven't developed best-practices yet of what information should go into what layer at what times. Increasing the overall context window is nice, but IMHO won't help us much.