I had this in my comment but deleted it, maybe you were responding to it, but in case you didn't see it: I found multiplayer browser games to be a good example of a hard project that LLMs help a lot with so that you can focus on the rewarding part.

LLMs can one-shot pretty good server-authority + client-prediction + rollback netcode, something I've probably spent weeks of my life trying to build and mostly failing. And they can get a basic frontend 'proof' working. And once you verify that the networked MVP works, you can focus on the game.

But the cool thing about multiplayer games is that they can be really small in scope because all of the fun comes from mechanics + playing with other people. They can be spaceships shooting at each other in a single room or some multiplayer twist on a dumbed down classic game. And that's just so much more feasible than building a whole game that's expected to entertain you as a single player.