John Paul Wile

I break things quickly and write about AI tech.

Full-Stack Developer & Writer · Colorado Springs, CO

Latest Posts

View all →
Sep 17, 2026

Running an Uncensored Qwen 3.8 27B Cybersecurity Lab with Hermes

A practical local setup for authorized red-team and blue-team research on Windows, Linux, and macOS...

Sep 12, 2026

Build an AI Assistant That Can Help You With ADHD

A local setup for sorting out a busy head, getting started on things, and remembering where you left off. Using Hermes and Qwen 3.8, with instructions...

Aug 20, 2026

I Ran Qwen 3.8 27B on a Single RTX 5090. Here's What Actually Worked

262K context, an uncensored GGUF, native MTP, and a final result of ~133 tokens/sec on one consumer GPU....

About Me

Full-Stack Developer & Tech Lead from Colorado Springs. I build things, break them, and write about what I learn along the way.

Learn More

Stay Updated

Get my latest thoughts on AI, development, and technology delivered to your inbox.

Subscribe on Substack