FRONTIER: generalise A6 teacher reference (consistency with identity scrub)

Author: Atome LM Team

FRONTIER.md

@@ -144,8 +144,8 @@ PYTHONPATH=. python3 scripts/run_ab_sweep.py \
 - **A5.** Real silicon. Flash an RP2040 with the engine + this 60.8 K
   ckpt. Measure tokens/sec, Joules/token. **The headline number that
   turns the claim from "frontier" into a fact.**
-- **A6.** Distillation from a strong teacher (GPT-4 / Claude on
-  10 MB of curated narrow-domain text) into the same 60 K Atome.
+- **A6.** Distillation from a strong teacher LLM (10 MB of curated
+  narrow-domain text generated by a frontier model) into the same 60 K Atome.
   Open question: does the architecture advantage compound under
   distillation?
 - **A7.** Bug A fix (Python `generate` ↔ C `atome_generate`