diff --git a/intermediate_source/transformer_building_blocks.py b/intermediate_source/transformer_building_blocks.py
index 8b88707004..df2fb90f96 100644
--- a/intermediate_source/transformer_building_blocks.py
+++ b/intermediate_source/transformer_building_blocks.py
@@ -71,7 +71,7 @@
 # ===============================
 # First, we will briefly introduce the four technologies mentioned in the introduction
 #
-# * `torch.nested <https://pytorch.org/tutorials/prototype/nestedtensor.html>`_
+# * `torch.nested <https://pytorch.org/tutorials/unstable/nestedtensor.html>`_
 #
 # Nested tensors generalize the shape of regular dense tensors, allowing for
 # representation of ragged-sized data with the same tensor UX. In the context of
@@ -157,7 +157,7 @@
 #   skipped, performance and memory usage improve.
 #
 # We'll demonstrate the above by building upon the ``MultiheadAttention`` layer in the
-# `Nested Tensor tutorial <https://pytorch.org/tutorials/prototype/nestedtensor.html>`_
+# `Nested Tensor tutorial <https://pytorch.org/tutorials/unstable/nestedtensor.html>`_
 # and comparing it to the ``nn.MultiheadAttention`` layer.
 
 import torch