Trim limitations to scale-only note

README.md

@@ -128,10 +128,7 @@ python inference.py
 
 ## Limitations
 
-- **~150M** research / edge chat model — not frontier quality
-- Can **hallucinate**, repeat, fail simple arithmetic, lose multi-turn facts
-- **Safety is incomplete** — do not deploy without your own filters
-- Requires `flash-linear-attention` (GDN-2); **not GGUF / llama.cpp** compatible today
+- **Scale**: at ~150M parameters this is a research / edge model, not a frontier system
 
 ---