For what it's worth, while ChatGPT 4.5 is generally quite underwhelming, it is much better at jokes than all the other models I tested so far. (That includes the other openAI offerings and the Claudes and DeepSeek etc.)
That's not to say 4.5 is great at humour, just that it's far less embarrassing than these models used to be.
A Greek, a Dutch philosopher, and Ludwig Wittgenstein walk into a bar… Let test Claude 3.7 to finish the joke: