diff --git a/the_seventy_maxims_of_maximally_effective_machine_learning_engineers.myco b/the_seventy_maxims_of_maximally_effective_machine_learning_engineers.myco
index 874666f..9619b24 100644
--- a/the_seventy_maxims_of_maximally_effective_machine_learning_engineers.myco
+++ b/the_seventy_maxims_of_maximally_effective_machine_learning_engineers.myco
@@ -41,7 +41,7 @@ Based on [[https://schlockmercenary.fandom.com/wiki/The_Seventy_Maxims_of_Maxima
 *. There’s a difference between spare GPUs and GPUs you’ve accidentally mined Ethereum on.
 *. Not all NaN is a bug – sometimes it’s a feature.
 *. “Do you have a checkpoint?” means “I can’t fix this training run.”
-*. “They’ll never expect this activation function” means “I want to try something non-differentiable.”
+*. “We propose a novel method” means “This has no sound mathematical basis.”
 *. If it’s a hack and it works, it’s still a hack and you’re lucky.
 *. If it will run inference, it will double as a space heater.
 *. The size of the grant is inversely proportional to the reproducibility of the results.