We got Claude to teach open models how to write CUDA kernels!

The best thing about agent skills is upskilling your agents on hard problems. There are two ways to look at that:

  1. You can take Opus 4.5 or other SOTA models and tackle the hardest problems out there.
  2. You can take models that run on your laptop and upskill them to harder problems. In this blog post, we’ll show you how to take on the latter.

This blog post walks through the process of using a new tool, upskill, to generate and evaluate agent skills with large models and use them with smaller models. We will benchmark upskill on

 

 

 

To finish reading, please visit source site