This paper presents a method based on genetic algorithms to find a solution for a standard biomechanical problem of human neck loads equilibrium using fourteen muscles at C4/5 level. The method starts from the widely used approach of minimizing intensities per area unit, which requires the feedback of the objective function output, and then minimizing the total force generated by the neck muscles. The results obtained are correlated with results presented in scientific literature. The feedback in the GA process is an innovation that could be applied to other kind of problems.