by Mxbonn on 2/15/23, 11:01 AM with 51 comments
by a13o on 2/15/23, 1:01 PM
For another example of why this isn't commercially viable, look at what happened with Super Mario Maker. In that game _humans_ are given a fixed set of Mario doodads with which to build levels. But Nintendo kept the secret sauce for themselves - the ability to create new doodads. What follows is millions of derivative Mario levels unworthy of their own game. Even if you trained MarioGPT on the rich set of level data available in Mario Maker, you would not have an algorithm that makes commercially viable Mario levels.
by mtlmtlmtlmtl on 2/15/23, 12:29 PM
by vyrotek on 2/15/23, 3:41 PM
https://store.steampowered.com/app/210870/Cloudberry_Kingdom...
by nomilk on 2/15/23, 1:16 PM
Incidentally, there's a nice example of a text representation of a level in the source code (requires scrolling horizontally, which isn't totally obvious from the GitHub UI): https://github.com/shyamsn97/mario-gpt/blob/main/mario_gpt/l...
Some parts are recognisable, for example the flag pole (which is typically at the end of mario levels, I believe).
by jhoelzel on 2/15/23, 1:01 PM
On another thought: this could probably replace the chrome dino pretty well
by gigel82 on 2/15/23, 6:13 PM
But I'm not convinced the results are any smarter than a randomized procedural generation (I'm sure using it for text generation instead will yield sub-par results).
by sylware on 2/15/23, 1:05 PM
by tantalor on 2/15/23, 2:51 PM
by rolenthedeep on 2/15/23, 10:47 PM
by anthk on 2/15/23, 8:29 PM