LLMs can be absolutely exhausting15 Mar, 2026Some days I get in bed after a tortuous 4-5 hour session working with Claude or Codex wondering what the heck happened. I'm tired & experiments are too slowAs I get more tired, the quality of my prompts degradeThis one seems pretty obvious. Feedback loop is too slow and context is bloatedSome of the work I'm doing right now requires parsing some large files. Recognizing slow feedback loops and making those the problemIn the case of my parsing problem I mentioned above, it was too slow and the feedback loop was painful. That was too time consuming, and also, I was getting paid even if my feedback loop wasn't perfect.