Santiago Valdarrama posted advice on building AI apps. He listed three strategies that lead to trouble: always calling the best model, which becomes very expensive; always calling the cheapest model, which he called dumb; and always calling a mid model, which produces mediocre results. Valdarrama stated the proper solution is to use a router that decides which model to call for each request. The post comes from the computer scientist and ML educator who teaches production AI/ML engineering.