Heidi AI matches frontier model using clinician‑feedback fine‑tuning
Heidi Health fine‑tuned a compact clinical AI model using blind clinician preference data, safety checks, and real‑world feedback, achieving parity (49.9% win rate) with the larger frontier model Sonnet 4.6 in side‑by‑side tests. The result shows that targeted reward signals can replace sheer model scale for high‑quality clinical answers.