Diego Pacheco Tech blog

More tokens are not more intelligence. Still, it is easy to get hooked on token usage. Is it learning, experimentation, or just FOMO? Subscription models trained us to extract as much as possible from a fixed monthly payment. But when more usage creates more code to review, why do we need to max everything out? Are we getting more from AI? Or are we repeating an old consumption habit with a new resource? I was reading and watching Gergely Orosz’s conversation with Dex Horthy, “Context engineering with Dex Horthy” , and it made me think about fast loops, slow loops, token harder, and token smarter. Faster loops do not necessarily accelerate value delivery. Unless the lead time decreases and the value increases, we may be trapped in local optimization.

Complexity is everywhere. Small, medium, or big company, does not matter, no one can escape complexity. Complexity just tends to get bigger, we depend on software more and more. Ask yourself, if your subscriptions on iPhone are increasing or decreasing in the last 5 years. There is more competition, and more streaming providers, and everything becomes a subscription, from grocery to transportation to even video games. Complexity increases, maintainability decreases, and maintaining software becomes harder. More software, more complexity. Complexity needs to be fought 24x7 at all times. However, how can we figure out something if we don't fully understand it? Is easy to just give up and do whatever since there is no escape, but there is a better way, we can do better. So what is complexity after all?