Update README.md

README.md

@@ -7,4 +7,70 @@ sdk: static
 pinned: false
 ---
 
-Edit this `README.md` markdown file to author your organization card.
+# 🌼 DaisyChainAI
+
+**Modular minds, not monoliths.** We build capable systems by *daisy-chaining* a handful of
+small, sharp specialists behind a learned router — instead of training one giant model to do
+everything. Each specialist is cheap, swappable, and crisp on its own domain; chained together,
+they behave like one model at a fraction of the active compute.
+
+---
+
+## 🔗 What "daisy-chaining" means
+
+A **daisy chain** links independent units in series so a signal can flow from one to the next,
+each unit handling what it's good at and passing the rest along. That's exactly how our systems work:
+
+- **Each link is one small specialist** — a dense ~74M model trained on a *single* domain. It is
+  excellent at its own data and (deliberately) surprised by everything else.
+- **The router is the connector between links.** When an input arrives, it travels down the chain:
+  every specialist reports how *surprised* it is (bits/base) and exposes its hidden state, and a tiny
+  learned router hands the work to the link that's most at home with it.
+- **The chain grows link by link.** Because the specialists are trained *separately*, you can chain a
+  new domain on without retraining the others — add a link, extend the router, done. Remove or upgrade
+  a single link the same way.
+- **One link runs per query.** Only the routed specialist computes, so a chain of four ~74M experts
+  costs ~74M of compute per token — roughly **7× cheaper** than a 500M monolith of comparable scope.
+
+So "DaisyChain" is both the brand and the mechanism: **a chain of specialists, connected by routing,
+that you extend one flower at a time.**
+
+---
+
+## 🛠️ How the models are built
+
+Each specialist is grown by **interleaving two steps**, per domain:
+
+1. **Continued pretraining** — next-token training on *only* that domain's data, so the specialist
+   becomes genuinely crisp on its home distribution (and the router can tell the links apart).
+2. **Per-domain distillation** — the specialist is distilled from a larger teacher foundation model
+   *restricted to its own domain* (soft-target KD, plus a factorized per-nucleotide variant where the
+   teacher supports it). It learns the teacher's behavior on its slice without ever becoming a generic
+   clone — the specialization is what makes routing work.
+
+We iterate those two steps until each link is as strong as its capacity allows, then train the
+**router**: a small head that reads every specialist's surprise plus a compressed view of its hidden
+state and predicts the home domain — recovering bias-corrections a plain "lowest-perplexity-wins" rule
+misses.
+
+This is, in lineage, a **cluster Branch-Train-Merge (cBTM) mixture of domain experts** — independent
+experts + perplexity-aware routing — with iterative distillation from a larger teacher layered on top.
+
+---
+
+## 🧬 Current project — DaisyChain Genomics
+
+Four DNA/RNA specialists (**eukaryote · prokaryote · mRNA · mRNA-splice**, ~74M each, **≈295M total —
+under 500M**), each distilled per-domain from a 500M genomic foundation model, behind a learned router.
+
+| | |
+|---|---|
+| **Routing accuracy** (held-out) | **94.8%** |
+| **Active params / query** | ~74M (one specialist) |
+| **vs the 500M teacher** | within ~6% likelihood; closing with training |
+
+- 📦 **Model:** [`DaisyChainAI/daisychain-genomics`](https://huggingface.co/DaisyChainAI/daisychain-genomics)
+- 🎮 **Live demo:** [`Daisychain-Genomics-Demo`](https://huggingface.co/spaces/DaisyChainAI/Daisychain-Genomics-Demo) — paste DNA, watch the chain light up specialist-by-specialist and route in real time.
+
+More links on the chain — and more chains — coming. 🌼
+