diff --git a/.gitignore b/.gitignore
index 1377554..a8d2fe8 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1 +1,2 @@
 *.swp
+.aider*
diff --git a/autograd/two_layer_net_autograd.py b/autograd/two_layer_net_autograd.py
index 2a5bb7f..9abe870 100644
--- a/autograd/two_layer_net_autograd.py
+++ b/autograd/two_layer_net_autograd.py
@@ -13,7 +13,7 @@
 through the graph to compute gradients of some downstream (scalar) loss with
 respect to a Tensor. Concretely if x is a Tensor with x.requires_grad == True
 then after backpropagation x.grad will be another Tensor holding the gradient
-of x with respect to some scalar value.
+of scalar (usually loss) with respect to x.
 """
 
 device = torch.device('cpu')