This certainly fits with my experience and biases. When using Copilot, I felt that it tried to be too clever, and often got things wrong. It would try to write a function based on the name, and would go one of three ways: either the function was a trivial one-liner and it saved me ~2 seconds of typing after I figured out if it was correct, or it was a complex function where it cost me ~2 seconds to figure out it was waaaaay off the mark, or it saved me 30 seconds up-front by producing something that appeared correct, but that I found out 10 minutes of debugging later was actually subtly incorrect in a way that I couldn't spot when reading quickly, but likely wouldn't have written myself.

What I really want is a smarter intellisense, whereas Copilot is a dumber pair programmer. I want smart, style-aware, context-aware tab completion on boilerplate, not on business logic.

Unfortunately I think many people are using it for business logic and that seems to be the direction the product is going.