We're all just impressed that it's even possible. No one is saying these are fun.

I guess the next question is if they can be made fun without too much additional work with a human guiding the AI.

How well encoded is "good game feel" in the weights of an LLM. I am guessing not very well.

> the next question is if they can be made fun without too much additional work

They can't. If you think about how these things are trained it's blatantly obvious fun is an impossible metric to optimize them for

Training impossibilities aside, how would you even make an optimization loop for "fun"?

Brain-computer interface, maybe. Hook a million play-testers up to the output and have it iterate.

..feels like there was a black mirror episode about that though

Unfortunately people are saying they are fun for the purposes of ragebait that goes viral, which is half the reason people intentionally post AI slop on social media.