Homelab adventures, infrastructure deep-dives, and lessons learned building enterprise-grade systems on a budget
A single config file can turn your Linux desktop into an expensive paperweight. Here's how NoMachine's bundled libraries broke my system and how to fix it.
Using agreement among frontier models (Claude, GPT-5, Gemini) as a training signal to build AI that's genuinely capable, not just benchmark-optimized
I stitched together Temporal, Mattermost, and three CLI agents to turn a paper into a shipped repo.
We fine-tuned a security agent to 100% skill differentiation in probing tests, but it collapsed to a single behavior in deployment. This gap led us to develop a trust diagnostic framework.
A follow-up to my retracted post on self-improving models. The fidelity metric improved 18% but actual performance dropped 11%. Here's what went wrong, what I learned about Goodhart's Law, and why reproducibility filtering might be the answer.
How I built custom Mojo kernels for AI research that outperform PyTorch on consumer hardware