AMP Tadpole v0.2.0: card (limitations, link to the Demo)

README.md

@@ -23,6 +23,10 @@ AMP Tadpole is trained from scratch on the
 [AMP Toy Robotics Benchmark](https://github.com/Adaptive-Machine-Patterns/amp-toy-robotics), and is
 the first model of [Adaptive Machine Patterns](https://adaptive-machine-patterns.com).
 
+**Try it in your browser:** the
+[AMP Embodied AI Workbench Demo](https://huggingface.co/spaces/Adaptive-Machine-Patterns/amp-embodied-ai-workbench-demo) runs AMP
+Tadpole live (through ONNX), and shows it inside, layer by layer.
+
 > **v0.2.0 is a preview.** Later versions will be published under new
 > tags (see [Versions](#versions)).
 
@@ -149,7 +153,19 @@ teacher whose action is a fixed function of the state.
   colours and 5 shapes. It has not seen a real camera.
 - It reads only canonical clauses (`instructions.json`); the benchmark
   rewrites free text into canonical form first.
-- The midpoint instruction is its weakest (75%; see Results).
+- The midpoint instruction is its weakest (75%; see Results). It is not
+  overfitting: on teacher-labelled samples its errors are the same on
+  scenes it trained on and scenes it never saw. Midpoint is simply less
+  well learned. Its target is an empty spot between two objects, so there
+  is nothing to aim at in the pictures, and it is 10% of the training
+  clauses; its error was still shrinking when training ended.
+- **What these results do not show.** The teacher is deterministic and
+  unlimited and the cameras are fixed: that is why a 6.5M-parameter model
+  does well here. It is not evidence against larger VLAs on benchmarks of
+  human demonstrations, which are varied, finite and often use a wrist
+  camera.
+- All results come from one training run; it has not been repeated with
+  other random seeds.
 
 ## Versions