GPT-4 is surprisingly good at explaining jokes

Explaining a joke, as E.B. White once wrote, is like dissecting a frog: "the thing dies in the process and the innards are discouraging to any but the purely scientific mind." In fact, the large language model -- released on March 14 by OpenAI -- is surprisingly good at generating detailed explanations of why a joke is funny. And like its predecessor, ChatGPT, the AI can also generate jokes, though its go-to one-liners are simple and seem to have been scraped from the internet's corniest, punniest corners (Why don't scientists trust atoms? Because they make up everything!). GPT-4 seems better at explaining humor than its predecessor.