Everyone likes to trash machine learning because the power requirements are high, but what they don’t realize is that we’re in the very first days of this technology. Every technology that got bundled together into your phone was equally as useless when it was first invented.

Literally once a week, I see some news story about AI researchers delivering an order of magnitude speedup in some aspect of AI inference. The technique described here apparently allows for a 20x speedup on GPU’s.