Nobody tells you what building alone actually feels like. The blog posts make it sound clean. You have an idea, you build it, you launch. Maybe you hit some technical walls, you push through, and eventually things work out. What they skip is the pa...

I've been building GhostLM — a decoder-only transformer trained from scratch in PyTorch on cybersecurity data. No pretrained weights, every component hand-written. A few weeks ago I published a post about fixing a leaky train/val split that made my ...

I've been building GhostLM for the past few months — a decoder-only transformer trained entirely from scratch in PyTorch on cybersecurity data. No pretrained weights, no HuggingFace wrappers. Every component hand-written. Phase 1 looked promising. Af...