Articles
Research
Reverse-Engineering the B200's Tensor Core, One Bit at a Time
We formally prove optimized ML kernels correct instead of testing them: symbolic execution shows a FlashAttention tile is equivalent to naive attention at d=64
July 11, 2026
Research
One Model Per Customer Shouldn't Mean One GPU Per Customer
Every customer wants their own model. Here's how to hand them one without buying a GPU per customer.
May 17, 2026
Infrastructure
We Got Sick of "Works on My Machine"
Remember when local development was supposed to be simple?
January 15, 2026
Train the models only you can build. One stack for enterprise post-training and frontier pre-training.
All System Operational© 2026 San Francisco Tensor Company
