Absolutely agree. "Make this faster" even with a solid way to measure progress is often fraught. It kept doing some very strange micro improvements that never improved the performance in the large but greatly improved complexity. I was _very_ much in the loop on a recent performance improvement I made. I really tried to walk away and let it find me the answer, but in the end I strongly guided it. As a lab assistant it was a huge help, but it messed up finding the improvement a number of times until I finally strongly intervened.