I've started using Microsoft's TROCR (another transformer OCR model) to read the cursive in my pocket journal (I have a habit of writing programs there first while I'm out and then typing them in manually, I just focus better that way.)
It's surprisingly accurate although you have to write your own program to segment the image into lines. I think with some fine tuning I could have the machine read my notebook with minimal corrections.
I managed to log into the mail account I had when I set up gmail.
Their AI arbitrarily decided that still wasn't good enough and that was the end of the gmail account I had since I was 13 (yes, I got one of the early invites.) I'm absolutely never doing anything important on a Google service ever again. It doesn't matter if you set stuff like that up.
The justification for these things is that the oxygen is being converted to CO2 faster than CO2 is being reduced back to oxygen. So if you capture CO2 at a high rate eventually this would lead to you capturing all of the oxygen.