Add hackathon submission tags, demo video, and launch post to README

Track: Backyard AI
Prizes/badges: Best Use of Modal, Best Demo, Tiny Titan, Off Brand
Links: Loom demo video + X launch post

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

README.md

@@ -14,6 +14,11 @@ tags:
   - kids
   - education
   - math
+  - Backyard AI
+  - Best Use of Modal
+  - Best Demo
+  - Tiny Titan
+  - Off Brand
 ---
 
 # 🦁 NumZoo
@@ -32,6 +37,8 @@ A mental math app for kids — answer questions, earn cute AI-generated animal i
 
 ### See it in action
 
+▶️ **[Demo video (Loom)](https://www.loom.com/share/c565cba49f2c4ad1bfb428e38ff4b629)** · 📣 **[Launch post](https://x.com/goooums/status/2066500943676399814)**
+
 | 1 · Pick animals & places | 2 · Solve math | 3 · Earn cute reward |
 |:---:|:---:|:---:|
 | ![picker](docs/app_picker.jpg) | ![quiz](docs/app_quiz.jpg) | ![reward](docs/app_reward.jpg) |
@@ -77,7 +84,7 @@ More rewards from the LoRA:
    [`scripts/generate_dataset.py`](scripts/generate_dataset.py) and
    [`training/`](training/) for the images + captions.
 2. **Training** — LoRA (rank 32, 1500 steps) on `FLUX.2-klein-base-4B` via
-   [ostris/ai-toolkit](https://github.com/ostris/ai-toolkit) on a **Modal** A100 (~45 min).
+   [ostris/ai-toolkit](https://github.com/ostris/ai-toolkit), running on a **[Modal](https://modal.com) A100** (~45 min, serverless GPU).
    Reproducible setup in [`training/lora_trainer/`](training/lora_trainer/).
 3. **Inference** — the LoRA loads on the distilled 4-step klein in `image_generator.py`;
    the app simply prepends the `NUMZOO` trigger to every prompt.