No, he would still say that. In the theoretical population genetics course I used to teach, I would often start out by imagining what a predictive theory of evolution would look like. We’d have genomics, with full sequences of all individuals in the species. We’d know what the genetic variations in all sites would do the phenotype (including behavior). We’d know the whole ecology of the species, so we could know what fitnesses those phenotypes had. But that means that we would need a complete understanding of the developmental biology, of neurobiology, and of ecology. For now we don’t have anything like that. So there is a long way to go. But of course that does not mean that our understanding of population genetics should be discarded.