[fzeroracer]

It does not understand humor. LLMs respond affirmatively to whatever input you give it and use the elements of whatever you feed it to try and explain. That's the core mistake the article makes and why that specific point is wrong. Let me demonstrate.

I asked the LLM the following prompt: Can you explain why the joke "Where's the joke?" is funny?

The response: "The humor in the joke "Where's the joke?" is derived from its meta or self-referential nature. The joke plays with the expectation of a traditional joke setup and punchline structure. Typically, when someone tells a joke, there is an expected punchline that delivers the humor. However, in this case, the punchline is intentionally missing, and instead, the question "Where's the joke?" is posed."

All it's doing is the same thing when you ask it to summarize a piece of data. This isn't a joke or meant to be a joke, but by telling it to explain it as a joke/meme will cause the output to differ in and regurgitate a bunch of nonsense about humor. This isn't understanding humor.