ZPG winds up not being as interesting, I think, because it doesn't figure out how to take the core idea of raking and twist it into more interesting puzzles, which is the classic puzzle approach: find a clean core mechanic, and then escalate on it.
I know we're all shocked that a 1-page web app with the author byline "Gwern, Claude-5.5-opus" (and matching HTML metadata) may have had LLMs involved; good work by Pangram there exposing the imposture.
ZPG winds up not being as interesting, I think, because it doesn't figure out how to take the core idea of raking and twist it into more interesting puzzles, which is the classic puzzle approach: find a clean core mechanic, and then escalate on it.
No surprise there.
That aside, did you enjoy the game?