docs: add sim-to-real deployment architecture reference

docs: reorganize — 25 files → 4 focused docs

refactor: rewrite blog around product vision; fix UI for Gradio 6

docs: expand blog with purpose, sim-to-real framing, lightweight model goal

fix: reduce kl_coef to prevent training instability

Rebuild as Life Simulator: 5 meters, 3 hidden profiles, GRPO training pipeline

Reorganize docs: segregate Round 1 and Round 2

Add SPEC.md and hackathon reference docs