diff --git a/content/blog/comments_not_for_you.md b/content/blog/comments_not_for_you.md
index 2214dcf..80c44dc 100644
--- a/content/blog/comments_not_for_you.md
+++ b/content/blog/comments_not_for_you.md
@@ -66,7 +66,13 @@ will be very insistent that when code says to do X, the new code written
 should fit the "X model".
 {{< /sidenote >}}
 It should come as no surprise that agents that make use of verbose,
-decision-making-included comments succeed more frequently, and get
+{{< sidenote "left" "verbose-note" "decision-making-included" >}}
+Interestingly, this turn of phrase is uncommon in pre-existing human comments,
+which would make up the majority of the model's training data set. In
+my opinion, this points towards this being something more than a reflection
+of the "human style".
+{{< /sidenote >}}
+comments succeed more frequently, and get
 rewarded. The result: +50/-1 comment blocks in your diff. It is irrelevant
 whether these comments concisely describe the codebase; their intended
 audience can read and parse them instantly. The comments are not for you.