Discover insights, tutorials, and thoughts on technology, homelab, and development.
The original observation has grown. Three independent measurement instruments now converge on the same universal structure inside neural networks.
An overview of my ongoing research exploring transformer injectivity, self-improving models, and high-performance AI on an RTX 3090
How periodic sparse attention achieves O(n) complexity while maintaining model quality
A deep dive into Mojo, the MLIR-based language promising 35,000x speedups over Python. What it does well, where it falls short, and who should actually care.
How I achieved 100% token recovery from Mistral-7B hidden states and what it means for AI security
How I built custom Mojo kernels for AI research that outperform PyTorch on consumer hardware