I Fine-Tuned Gemma 4 to Detect Code Vulnerabilities
One GPU, one epoch, three evaluation surprises, and recall that jumped from 4% to 51%. If you want the concepts behind the decisions (LoRA, QLoRA, NF4, batch...
// 2026
Every Concept You Need Before Fine-Tuning an LLM
A practitioner’s reference — LoRA, QLoRA, batch size, loss curves, and output formats explained. This is the concepts companion to I Fine-Tuned Gemma 4 to De...
Your Brain on Scams: What the Experiment Actually Found
Part 2 of 2 — The results. Part 1 covered the theory and experiment design.
What Does a Scam Message Do to Your Brain? I Used Meta's AI to Find Out
Part 1 of 2 — The theory and the experiment design. Part 2 shows what actually happened.