But having AI extend your notes includes all the loss of the initial summarization, with extra AI randomness on top. It can't recover the information lost in the summary, that's what makes the summary lossy.
It can, in the way you can follow the abstract of a paper with its body. Don't forget that the model has access to the original text; it's not just going off the summary.
Why read Huckleberry Finn when you can read the cliffs notes?
Summarization is lossy, usually on the experiencing part.