couple more papers

docs/source/history.rst

@@ -1,6 +1,16 @@
 The science of scale
 =====================
 
+.. admonition:: Warning
+   :class: warning
+
+   This page is still under construction.
+
+.. admonition:: Warning
+   :class: seealso
+
+   This page was written by Jeremy and so is likely biased by his view of the world. He is putting this here because he thinks it provides a useful counterpoint to some prevailing narratives. If you'd like to mention some other work here, feel free to either make a pull request or reach out to us by email.
+
 some twists and turns
 
    | 📘 `On the distance between two neural networks and the stability of learning <https://arxiv.org/abs/2002.03432>`_
@@ -19,6 +29,12 @@ and more text
    |     Greg Yang, James B. Simon, Jeremy Bernstein
    |     arXiv 2023
 
+and more
+
+   | 📒 `Automatic gradient descent: Deep learning without hyperparameters <https://arxiv.org/abs/2304.05187>`_
+   |     Jeremy Bernstein, Chris Mingard, Kevin Huang, Navid Azizan, Yisong Yue
+   |     arXiv 2023
+
 and even more text
 
    | 📕 `Scalable optimization in the modular norm <https://arxiv.org/abs/2405.14813>`_