I've experimented a couple of times with generating candy heart messages using various kinds of machine learning algorithms. Originally, short messages were just about all the original text-generating neural networks could handle. Now we've come back around to approximately the same performance, yet with orders of
![Generated candy heart images. Messages include "le yas", "dove tut", and "hove".](/content/images/size/w795/2024/02/Screenshot-2024-02-10-at-12.21.44-PM.png)