Claude Opus 5 vs Qwen3.8

I ran an experiment. Have Qwen3.8 and Claude Opus 5 try to optimize a codebase for performance. I wanted to see which was better and how far the gap was between them.

These models are very different from one another. Opus 5 is one of the top frontier models. Qwen3.8 is a model I could run locally, in my case on a Framework Desktop. For the harnesses, I used the claude CLI and opencode (for Qwen3.8).

Going in I knew Opus was the better model. This wasn’t about finding the winner. It was about seeing how far local models have come and what I could squeeze out of Qwen3.8.

Continue Reading »


When Open Standards and Specs are Better Than Open Source

Open standards and specs are often more powerful than open source. Especially in the age of AI.

Open source has been a dominant force in software development and operations. It’s enabled the growth of Linux, Kubernetes, React, Node.js, and so many other projects that power modern day infrastructure, web applications, and more. Open source is significant. It’s enabled careers, it’s accelerated product development, it’s given people software to tinker with at home, and it’s helped people learn how to build software. I don’t want to downplay open source.

But, have you ever thought about …

Continue Reading »


Other Recent Posts: