Fundamental technique lets researchers use a big, expensive “teacher” model to train a “student” model for less.

The story <a href="https://www.quantamagazine.org/how-distillation-makes-ai-models-smaller-and-cheaper-20250718/">How Distillation Makes AI Models Smaller and Cheaper</a> first appeared on Quanta Magazine.

Ice Is Way More Complex Than It Seems

Exploring the distant universe, the insides of cells, the abstractions of math, the complexity of information itself, and much more, The Quanta Podcast is a tour of the frontier between the known and the unknown. In each episode, Quanta Magazine Editor-in-Chief Samir Patel speaks with the minds behind the award-winning publication to navigate through some of the most important and mind-expanding questions in science and math. Quanta specifically covers fundamental research — driven by curiosity, discovery and the overwhelming desire to know why and how. Join us every Tuesday for a stimulating conversation about the biggest ideas and the tiniest details.(If you've been a fan of the Quanta Science Podcast, it will continue here. You'll see those episodes marked as audio edition episodes every two weeks.)