That's the kicker, LLM driven stories are likely to fall into the same trap that "infinite" procedurally generated games usually do - technically having infinite content to explore doesn't necessarily mean that content is infinitely engaging. You will get bored when you start to notice the same patterns coming up over and over again.
Procgen games mainly work when the procedural parts are just a foundation for hand-crafted content to sit on, whether that's crafted by the players (as in Minecraft) or the developers (as in No Mans Sky after they updated it a hundred times, or Rougelikes in general).
Yeah, generative AI can create cool looking pictures and video but so far it hasn't managed to create infinitely engaging stories. The models aren't there yet.
I'd argue that the same principle applies to pictures, there are many genres of AI image that are cool the first time you see them, but after you've seen the exactly the same idea rehashed dozens of times with no substantial variety it starts wearing really thin. AI imagery is often recognizable as AI not just because of charactistic flaws like garbled text but because it's so hyper-clichéd.
I wonder if there's some threshold to be crossed where it can be surprising for longer. I made a video game name generator long ago that just picks a word (or short phrase) from each of three columns. (The majority of the words / phrases are from me, though many other people have contributed.)
I haven't added any words or phrases to it in years, but I still use it regularly and somehow it still surprises me. Maybe the Spelunky-type approach can be surprising for longer; that is, make a bunch of hand-curated bits and pick from them randomly: https://tinysubversions.com/spelunkyGen/
Procgen games mainly work when the procedural parts are just a foundation for hand-crafted content to sit on, whether that's crafted by the players (as in Minecraft) or the developers (as in No Mans Sky after they updated it a hundred times, or Rougelikes in general).