Research
Research
A running record of what I'm learning about AI — models, infrastructure, tooling, and everything underneath. Pick a topic. New entries get added as I go.
AI Infrastructure
The physical side of AI: the chips that do the math, the data centers that house them, the power they need, and the supply chain that builds it all.
6 entries · newest first
- Power from space, and the nuclear backup planOct 2026
- The AI stack: from app to GPUOct 2026
- CPU, GPU, TPU, DPU: the chips behind AIOct 2026
- How AI Data Centers Get BuiltOct 2026
- What It Takes to Keep AI RunningSep 2026
- Silicon to SuperclusterAug 2026
Inference & serving
What happens when a model is actually used: how your question turns into an answer, and what it takes to serve lots of people at once. A new page lands here each time I finish a lesson.
1 entry · newest first
Open Inference & serving →