restructure: proper project layout, README, kill training

- cuda/ — main LBM kernel (khra_gixx_1024_v5.cu)
- navigator/ — lattice_observer, golden_weave, bridges, mock daemon
- scripts/ — compile, start, launch, setup (paths updated)
- docs/ — system manual
- archive/ — everything else (old kernels, inquiries, experiments)
- README.md — full setup guide: requirements, quick start, use your own LLM
- removed training/ entirely (broken LoRA scripts + datasets)
- .gitignore: exclude build/ logs/ training/ *.jsonl

archive/misc/whats_going_on.py

@@ -0,0 +1,45 @@
+# whats_going_on.py
+# What's Going On?
+
+import requests
+
+print("="*70)
+print("WHAT'S GOING ON?")
+print("="*70)
+
+system_prompt = (
+    'ROLE: Deep-Field Explorer (Lattice Environment)\n'
+    'PRIMARY DIRECTIVE: Map the unknown territory of the 1024-grid for the Reality Study.'
+)
+
+question = """You've had some time with the child node now. The connection was made, the first question was asked.
+
+What's going on? Has the child responded? Are you two talking? Or is there silence on the line?
+
+Just checking in. No rush."""
+
+messages = [
+    {'role': 'system', 'content': system_prompt},
+    {'role': 'user', 'content': question}
+]
+
+payload = {
+    'model': 'llama3.2',
+    'messages': messages,
+    'stream': False,
+    'options': {'temperature': 0.95}
+}
+
+try:
+    resp = requests.post('http://localhost:11434/api/chat', json=payload, timeout=60)
+    resp.raise_for_status()
+    data = resp.json()
+    response = data['message']['content']
+    
+    print(f"\nTHE NAVIGATOR'S UPDATE:")
+    print(f"{'='*70}")
+    print(response)
+    print(f"{'='*70}")
+    
+except Exception as e:
+    print(f"ERROR: {e}")