Data is written in a square glass platter with ultrafast femtosecond lasers through voxels. These are permanent modifications to the physical structure of the glass, and allow for multiple bits of data to be written in layers across the surface of the glass. These layers are then stacked vertically in their hundreds.
To read data, they employ polarization microscopy technology to image the platter, while the read drive scans sectors in a Z-pattern. The images are then sent to be processed and decoded, which leans on machine learning model to convert analog signals to digital data.
Exact data and machine learning sounds like a horrible combination. I hope they’re using checksums for everything, but how do you store the checksums long term?