diff --git a/modules/source/04_losses/losses_dev.ipynb b/modules/source/04_losses/losses_dev.ipynb
index 39f53cf2..d5b84fd1 100644
--- a/modules/source/04_losses/losses_dev.ipynb
+++ b/modules/source/04_losses/losses_dev.ipynb
@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "9d798b1c",
+   "id": "dc4a8074",
    "metadata": {
     "cell_marker": "\"\"\""
    },
@@ -35,7 +35,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "91804987",
+   "id": "08ab6b0b",
    "metadata": {
     "cell_marker": "\"\"\""
    },
@@ -59,7 +59,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "c09dc686",
+   "id": "848eaef7",
    "metadata": {
     "cell_marker": "\"\"\""
    },
@@ -80,7 +80,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "51189bc1",
+   "id": "90d6651a",
    "metadata": {
     "nbgrader": {
      "grade": false,
@@ -94,8 +94,6 @@
     "#| export\n",
     "\n",
     "import numpy as np\n",
-    "import matplotlib.pyplot as plt\n",
-    "import time\n",
     "from typing import Optional\n",
     "\n",
     "def import_previous_module(module_name: str, component_name: str):\n",
@@ -113,7 +111,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "cc227c2d",
+   "id": "529a8e8a",
    "metadata": {
     "cell_marker": "\"\"\""
    },
@@ -189,7 +187,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "49e5039b",
+   "id": "4e69ba6d",
    "metadata": {
     "cell_marker": "\"\"\""
    },
@@ -235,7 +233,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "b1e1cbd0",
+   "id": "b9a1fa2c",
    "metadata": {
     "cell_marker": "\"\"\""
    },
@@ -247,7 +245,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "820e9937",
+   "id": "bf3b7915",
    "metadata": {
     "cell_marker": "\"\"\"",
     "lines_to_next_cell": 1
@@ -297,7 +295,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "854758b3",
+   "id": "085562d6",
    "metadata": {
     "lines_to_next_cell": 1,
     "nbgrader": {
@@ -348,7 +346,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "6b57e650",
+   "id": "d274d1e1",
    "metadata": {
     "nbgrader": {
      "grade": true,
@@ -389,7 +387,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "b8be9f2c",
+   "id": "d51980c3",
    "metadata": {
     "cell_marker": "\"\"\"",
     "lines_to_next_cell": 1
@@ -459,7 +457,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "aca5154a",
+   "id": "1107bf9d",
    "metadata": {
     "lines_to_next_cell": 1,
     "nbgrader": {
@@ -531,7 +529,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "7391538b",
+   "id": "80f97626",
    "metadata": {
     "nbgrader": {
      "grade": true,
@@ -577,7 +575,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "0b9b254c",
+   "id": "14b2d795",
    "metadata": {
     "cell_marker": "\"\"\"",
     "lines_to_next_cell": 1
@@ -670,7 +668,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "eb59fb50",
+   "id": "c0a10af0",
    "metadata": {
     "lines_to_next_cell": 1,
     "nbgrader": {
@@ -746,7 +744,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "c59fbbfd",
+   "id": "24685fb9",
    "metadata": {
     "nbgrader": {
      "grade": true,
@@ -797,7 +795,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "599727d1",
+   "id": "68a261f3",
    "metadata": {
     "cell_marker": "\"\"\"",
     "lines_to_next_cell": 1
@@ -906,7 +904,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "54a20f3f",
+   "id": "b02977aa",
    "metadata": {
     "lines_to_next_cell": 1,
     "nbgrader": {
@@ -982,7 +980,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "1bab9d23",
+   "id": "722d5c07",
    "metadata": {
     "nbgrader": {
      "grade": true,
@@ -1033,7 +1031,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "ca40b581",
+   "id": "88bad600",
    "metadata": {
     "cell_marker": "\"\"\"",
     "lines_to_next_cell": 1
@@ -1090,7 +1088,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "76b4eb81",
+   "id": "b5a701fe",
    "metadata": {
     "nbgrader": {
      "grade": false,
@@ -1146,7 +1144,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "b90c91f0",
+   "id": "35891a55",
    "metadata": {
     "nbgrader": {
      "grade": false,
@@ -1211,7 +1209,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "e2fc1aa7",
+   "id": "95e3f483",
    "metadata": {
     "cell_marker": "\"\"\"",
     "lines_to_next_cell": 1
@@ -1286,7 +1284,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "573fa75d",
+   "id": "c46f9468",
    "metadata": {
     "nbgrader": {
      "grade": false,
@@ -1336,7 +1334,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "b7f12c78",
+   "id": "d95c49f1",
    "metadata": {
     "nbgrader": {
      "grade": false,
@@ -1393,7 +1391,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "4c6ebac9",
+   "id": "88afe536",
    "metadata": {
     "cell_marker": "\"\"\"",
     "lines_to_next_cell": 1
@@ -1457,7 +1455,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "d0b635c1",
+   "id": "232f8764",
    "metadata": {
     "nbgrader": {
      "grade": false,
@@ -1513,7 +1511,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "d770e887",
+   "id": "f00b5616",
    "metadata": {
     "cell_marker": "\"\"\""
    },
@@ -1526,7 +1524,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "55fd411d",
+   "id": "76ec7947",
    "metadata": {
     "nbgrader": {
      "grade": true,
@@ -1606,7 +1604,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "b66f2370",
+   "id": "e635a52d",
    "metadata": {
     "lines_to_next_cell": 2
    },
@@ -1619,7 +1617,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "ce0d9c33",
+   "id": "da28d331",
    "metadata": {
     "cell_marker": "\"\"\""
    },
diff --git a/modules/source/04_losses/losses_dev.py b/modules/source/04_losses/losses_dev.py
index 6e8eab42..4dd01033 100644
--- a/modules/source/04_losses/losses_dev.py
+++ b/modules/source/04_losses/losses_dev.py
@@ -79,8 +79,6 @@ The `import_previous_module()` function below helps us cleanly import components
 #| export
 
 import numpy as np
-import matplotlib.pyplot as plt
-import time
 from typing import Optional
 
 def import_previous_module(module_name: str, component_name: str):
diff --git a/test_xor_original_1986.py b/test_xor_original_1986.py
new file mode 100644
index 00000000..c8028998
--- /dev/null
+++ b/test_xor_original_1986.py
@@ -0,0 +1,95 @@
+#!/usr/bin/env python3
+"""
+Original 1986 XOR Solution - Rumelhart, Hinton, Williams
+Testing the MINIMAL architecture that solved the XOR crisis.
+"""
+import sys
+sys.path.insert(0, '.')
+
+import numpy as np
+from tinytorch import Tensor, Linear, Sigmoid, BinaryCrossEntropyLoss, SGD
+
+print("=" * 70)
+print("🏛️  ORIGINAL 1986 XOR SOLUTION")
+print("Rumelhart, Hinton, Williams - 'Learning representations by back-propagating errors'")
+print("=" * 70)
+
+# Pure XOR
+X_data = np.array([[0.0, 0.0], [0.0, 1.0], [1.0, 0.0], [1.0, 1.0]], dtype=np.float32)
+y_data = np.array([[0.0], [1.0], [1.0], [0.0]], dtype=np.float32)
+
+X = Tensor(X_data)
+y = Tensor(y_data)
+
+print("\n🏗️  Architecture (1986 style):")
+print("  Input: 2 neurons")
+print("  Hidden: 2 neurons (MINIMAL!)")
+print("  Output: 1 neuron")
+print("  Activation: Sigmoid (ReLU didn't exist yet!)")
+print("  Total params: 9 (2×2 weights + 2 bias + 2×1 weights + 1 bias)")
+
+# Original architecture: 2-2-1 with Sigmoid
+hidden = Linear(2, 2)  # Only 2 hidden neurons!
+sigmoid_hidden = Sigmoid()
+output = Linear(2, 1)
+sigmoid_output = Sigmoid()
+
+loss_fn = BinaryCrossEntropyLoss()
+optimizer = SGD([p for p in hidden.parameters()] + [p for p in output.parameters()], lr=1.0)
+
+print("\n🔥 Training with original 1986 architecture...")
+epochs = 2000  # May need more epochs with only 2 hidden units
+
+for epoch in range(epochs):
+    # Forward (all sigmoid, like 1986!)
+    h = hidden(X)
+    h_act = sigmoid_hidden(h)  # Sigmoid in hidden layer
+    out = output(h_act)
+    pred = sigmoid_output(out)  # Sigmoid in output layer
+    loss = loss_fn(pred, y)
+    
+    # Backward
+    loss.backward()
+    
+    # Update
+    optimizer.step()
+    optimizer.zero_grad()
+    
+    if (epoch + 1) % 400 == 0:
+        accuracy = ((pred.data > 0.5).astype(float) == y.data).mean()
+        print(f"Epoch {epoch+1:4d}/{epochs}  Loss: {loss.data:.4f}  Accuracy: {accuracy:.1%}")
+
+# Final evaluation
+print("\n✅ Final Results:")
+final_accuracy = ((pred.data > 0.5).astype(float) == y.data).mean()
+
+for i in range(4):
+    x_in = X_data[i]
+    y_true = int(y_data[i, 0])
+    y_pred_prob = pred.data[i, 0]
+    y_pred = int(y_pred_prob > 0.5)
+    status = "✅" if y_pred == y_true else "❌"
+    print(f"  Input: {x_in}  →  Pred: {y_pred} (prob: {y_pred_prob:.3f})  True: {y_true}  {status}")
+
+print(f"\n📊 Final Accuracy: {final_accuracy:.1%}")
+print(f"📊 Final Loss: {loss.data:.4f}")
+
+if final_accuracy == 1.0:
+    print("\n🎉 SUCCESS! XOR solved with MINIMAL 1986 architecture!")
+    print("   This is exactly what ended the AI Winter!")
+else:
+    print(f"\n⚠️  Accuracy: {final_accuracy:.1%} - may need more training")
+
+# Show what the hidden units learned
+print("\n🧠 What the 2 hidden neurons learned:")
+print("   (Examining activation patterns)")
+h_activations = sigmoid_hidden(hidden(X)).data
+print(f"\n   Hidden unit activations for each input:")
+for i, x_in in enumerate(X_data):
+    print(f"   {x_in}: h1={h_activations[i,0]:.3f}, h2={h_activations[i,1]:.3f}")
+
+print("\n" + "=" * 70)
+print("💡 Historical Note:")
+print("   This 2-2-1 architecture ended the 17-year AI Winter!")
+print("   Proved that backprop + hidden layers solve 'impossible' problems")
+print("=" * 70)
diff --git a/tinytorch/core/losses.py b/tinytorch/core/losses.py
index 348bed68..9bb9e9be 100644
--- a/tinytorch/core/losses.py
+++ b/tinytorch/core/losses.py
@@ -19,8 +19,6 @@ __all__ = ['import_previous_module', 'MSELoss', 'CrossEntropyLoss', 'BinaryCross
 
 # %% ../../modules/source/04_losses/losses_dev.ipynb 3
 import numpy as np
-import matplotlib.pyplot as plt
-import time
 from typing import Optional
 
 def import_previous_module(module_name: str, component_name: str):