[Der_Einzige]

Actually, they struggle even with haikus if you care about proper syllable counts.

[microtherion]

Same with limericks. When asked to produce villanelles, ChatGPT about half the time comes up with perfectly good ones, and half the time completely whiffs on the concept. ChatGPT seems to "know" that sestinas consist of stanzas of six lines each, but otherwise completely fails to follow the form.

[sdenton4]

This likely has to do with the tokenization of the sentences; the same reason it's bad at arithmetic.