MarioGPT hints at a glorious AI-generated future where we will all play Nintendo forever

techcrunch.com:

There can never be too much Mario in the world. Sure, it’s probably been a while since you played one of the original NES games, but probably because they’re so familiar. What if I told you researchers had created a way to generate infinite Mario levels so you can play a brand new one every day until the sun burns out?

A team at IT University of Copenhagen just released a (pre-pub) paper and Github page showing a new method for encoding and generating Super Mario Bros levels, which they call MarioGPT. (Somewhere in Redmond, a lawyer sips his coffee and begins typing.)

MarioGPT is based on GPT-2, not one of these newfangled conversational AIs. These large language models are good at not just taking in words in sentences like these and putting out more like them — they are general purpose pattern recognition and replication machines.

“We honestly just picked the smaller one to see if it worked!” said Shyam Sudhakaran, lead author on the paper, in an email to TechCrunch. “I think with small datasets in general, GPT2 is better suited than GPT3, while also being much more lightweight and easier to train. However, in the future, with bigger datasets and more complicated prompts, we may need to use a more sophisticated model like GPT3.”

Even a very large LLM won’t understand Mario levels natively, so the researchers first had to render a set of them  as text, producing a sort of Dwarf Fortress version of Mario that, honestly, I would play:

Each tile is rendered as a different character.

Want to make a buck? Mario in the terminal. Just saying.

Once the level is represented as a series of ordinary characters, it can be ingested by the model much the way any other series of characters can, be they written language or code. And once it