I just tried Claude Sonnet with the Pelican & Walrus setup, but asked it for something in style of Norm Macdonald's humor, which would seem a potentially good fit for this type of idea. It got the idea of a rambling story (cf Macdonald's moth joke) that mostly ignored them being a Pelican and Walrus, which seemed promising, but still failed to deliver. I'm guessing with some more guidance and iteration it could have come up with something.

I've been trying out "write and perform an MST3K episode reviewing your previous answer" as a prompt. Have yet to get a funny answer from any model.

Older base models produce some great stuff though, at least if you're me and think RoboRosewater and dril_gpt2 are funny.

I've found that the weaker the model, the more of an unhinged, LSD-trip response you get. I made a podcast years ago (https://deepdreams.stavros.io) and GPT-2 was definitely the more hilarious of the models.

> Have yet to get a funny answer from any model.

Just like the real thing! Promising results!

LLMs output can often be like a prism in front of a mirror - a fusion of humanity with the specific human, reflected back at the human.

Simon, perhaps you're just not funny.

How Nietzschian

I'd love to see a standup competition of trying to make AI jokes/sets funny.