Blog
Notes on signal processing, computing constraints, and engineering trade-offs.
Featured Articles
Why We Discovered Sparse Knowledge Distillation
How a Jenga tower taught me what's really going on inside large AI models.
Why SparseTech, Why Now?
Why dense computation solved the first problem, and why sparsity is the design step that follows.
Signal, Noise, and the Space Between
Opening up the engineering notebooks.
Latest Articles
AI Models Don't Need to Be Smaller. They Need to Be Selective
Scaling adds capacity. It doesn't guarantee structure. What we found when we started carving.
Why Learning From One Model Is Like Studying With One Teacher
Why learning from a single source creates limits, and why combining perspectives produces smarter, more reliable systems.
Why Prompting Feels Like Guesswork
The real problem isn't how you ask. It's how the model listens.
Why We Discovered Sparse Knowledge Distillation
How a Jenga tower taught me what's really going on inside large AI models.
Why SparseTech, Why Now?
Why dense computation solved the first problem, and why sparsity is the design step that follows.
Signal, Noise, and the Space Between
Opening up the engineering notebooks.