There's also the "horse riding astronaut" challenge in image generation: https://garymarcus.substack.com/p/horse-rides-astronaut-redu...

Gary Marcus is not the man to be looking to on this topic

	▲	AlphaAndOmega0 13 minutes ago \| parent [-]
		Gary Marcus successfully predicted all ten of the one AI Winters. He also claimed that LLMs were a failure because of prompts that GPT 3.5 couldn't parse, after the launch of GPT-4,which handled them with aplomb.