There are claims that it improves the LLMs on an array of benchmarks - if that is confirmed - wouldn't it be more important than the theory?
Above explains why it may work within the scope of theory despite being a poor method, but the success rate of methods like these is generally low enough to not be useful.
I'll give it more attention if they actually release conclusive benchmarks showing that it works instead of simply claiming it works, which is a big difference.