In the last few years, the dark matter field has bifurcated into experiments focused on wimp-scale dark matter with massive liquid noble detectors and experiments focused on so-called ‘hidden sectors’ dark matter, pushing small detectors to much lower energy resolutions. Low-mass dark matter searches, focusing on single eV-scale energy deposits, are sensitive to different backgrounds than their higher-threshold counterparts, including but not limited to infrared emissions from the experimental environment and low-rate cosmogenic contamination in the target materials. The traditional paradigm of 2-phase detectors used to discriminate between electronic and nuclear recoils is no longer effective, both because of experimental limitations and kinematic constraints. The low-mass reach of SuperCDMS SNOLAB is based on the idea of moving from a phonon+charge readout to a charge-mediated phonon readout; introducing degeneracy between our separate detection channels to achieve lower thresholds. In this talk I will discuss the theory behind the CDMS-HV detector technology and present exciting results from prototype detectors run at test facilities in the CDMS collaboration. I will then discuss the science reach given these results, and explore future directions with this technology.I will describe our development of a convolutional neural network (CNN) to learn to search for and characterize absorption lines in quasar spectra. Specifically, the algorithm discovers and measures the redshift and Hydrogen column density of damped Lya systems (DLAs). These systems dominate the neutral hydrogen gas of the universe, trace the interstellar medium of distant galaxies, and offer cosmological constraints on the build up of gas and heavy elements across cosmic time. I will discuss the lessons learned employing CNN techniques on large spectral datasets and the prospects for future analysis.