Align docs around LLM-driven scenario generation

docs/create_demo_video.py

@@ -54,12 +54,12 @@ def write_frames(writer, image: Image.Image, seconds: float) -> None:
 
 def main() -> None:
     cards = [
-        (title_card("LifeChoice Simulator", "A causal decision simulator, not another chatbot.\nQwen2.5-7B + Gradio + deterministic state."), 3.0),
+        (title_card("LifeChoice Simulator", "An LLM-powered causal decision simulator.\nQwen2.5-7B + Gradio + deterministic state."), 3.0),
         (screenshot_card("onboarding.png", "Start in seconds", "One concrete calibration answer takes you directly into the simulation."), 4.0),
-        (screenshot_card("simulation.png", "Immediate first scene", "The opening is deterministic; later nodes prefetch in the background."), 4.0),
+        (screenshot_card("simulation.png", "Adaptive future nodes", "A 7B model generates bounded scenarios while deterministic state keeps score."), 4.0),
         (screenshot_card("cascade.png", "Choices return later", "Facts, obligations, and closed options make branches materially different.", 500), 4.0),
         (screenshot_card("report.png", "A report grounded in behavior", "Five metrics, three cascade moments, and a bounded causal ledger.", 500), 4.0),
-        (title_card("Small model. Real state.", "7.616B parameters. No 32B+ fallback.\nBuilt with Codex for the Build Small Hackathon."), 3.0),
+        (title_card("Small model. Real state.", "7.616B scenario model. No 32B+ fallback model.\nBuilt with Codex for the Build Small Hackathon."), 3.0),
     ]
     with imageio.get_writer(
         OUT,