Research
We are researchers at heart. We love building things, and investing in the ones that work in a way nobody expected. These are the papers so far.
Cortad was called Brainsless before it was renamed, so the papers carry the Brainsless Research Lab name.
faster attention at a million tokens, from the law that a model reads a small, fixed number of memories per word
of ordinary RAM runs a million-token cache, instead of $180k of GPUs
tokens is where retrieval collapses, and why the memory we build is structured
tokens per second, single stream, trillion-parameter model on four GPUs, reproducible for about fifteen dollars
of what a model reads to write a single word comes from one small shared piece, 7% of the file, that everyone still ships at full size
