Upload README.md with huggingface_hub

README.md

@@ -11,11 +11,11 @@ short_description: Small models, narrow tasks
 
 # Glassbox
 
-Small models, narrow tasks. Trained from scratch, under 100M parameters, each doing one thing.
+Small models, narrow tasks.
 
-[restorer-interp-lab.iksnerd.workers.dev](https://restorer-interp-lab.iksnerd.workers.dev) — a live
-interpretability lab: watch the models think, one forward pass at a time.
+Trained from scratch, under 100M parameters, each doing one thing. The cards carry the
+losses as well as the wins.
 
-Every number behind them is reproducible: [bg-eval](https://github.com/iksnerd/bg-eval) re-runs
-the published results from the checkpoints alone, with no dependency on this project's training
-code.
+[restorer-interp-lab.iksnerd.workers.dev](https://restorer-interp-lab.iksnerd.workers.dev) ·
+[bg-eval](https://github.com/iksnerd/bg-eval), the loader and eval harness — reproduce the
+numbers on the cards yourself