I wish they never abandoned the goal of being a true Python superset. That would have been something.
Given that there are so many failed attempts to optimise arbitrary Python code, it was dubious from the start. Furthermore, the documentation completely ignored these challenges and made it clear that Mojo's goal was to compile to MLIR in order to write kernels for machine learning. The first example of Mojo code was a low level matrix multiplication kernel taking advantage of fancy compilation features and the documentation advertised pointers inspired by Rust's move semantics, neither of which are typically considered friendly or relevant to high level programmers.
From the roadmap:
>Mojo may or may not evolve into a full superset of Python, and it's okay if it doesn't.
But alas they dropped the goal and for me the ball with the decision to stop following this. I will probably not write mojo code when I could use Rust or Julia instead, which are more aligned with my necessities.