Andrey Lukyanenko
MiniMax Sparse Attention: Per-Group Block Selection for Cheap Million-Token Inference Paper Code Model Long-context LLMs keep promising the same thing: feed more tokens into the prompt and let the model reason over them. The bottleneck is rarely the window itself: it is the cost of attending...
Andrey Lukyanenko
Testing MiniMax M3 on real tasks: repo refactor, screenshot debugging, and Spotify recommendations I got early access to MiniMax M3, so I plugged it into Claude Code and used it to work on a few tasks that I wanted to complete for some time: a code audit and refactor of my old web game, two UI...
Alex Shtoff
Intro We continue our discussion of machine-learned models of the form \[f({\boldsymbol x};{\boldsymbol A}_{0:n}) = \lambda_k \Bigl({\boldsymbol A}_0 + \sum_{i=1}^n x_i {\boldsymbol A}_i\Bigr),\] where \({\boldsymbol A}_i\) are learned symmetric matrices, and \(\lambda_k\) is the \(k\)-th...