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 226b1d0..4e8e0da 100644
--- a/the_seventy_maxims_of_maximally_effective_machine_learning_engineers.myco
+++ b/the_seventy_maxims_of_maximally_effective_machine_learning_engineers.myco
@@ -33,7 +33,7 @@ Based on [[https://schlockmercenary.fandom.com/wiki/The_Seventy_Maxims_of_Maxima
 *. Only overfitters prosper (temporarily).
 *. Any model is production-ready if you can containerize it.
 *. If you’re logging metrics, you’re being audited.
-*. If you’re seeing NaN, you need a smaller learning rate.
+*. If you’re leaving GPUs unused, you need a bigger model.
 *. That which does not break your model has made a suboptimal adversarial example.
 *. When the loss plateaus, the wise call for more data.
 *. There is no “overkill.” There is only “more tokens” and “CUDA out of memory.”