For 30 years, Magic: The Gathering has been built on the innovation, ingenuity, and hard work of talented people who sculpt a beautiful, creative game. That isn’t changing. Our internal guidelines remain the same with regard to artificial intelligence tools: We require artists, writers, and creatives contributing to the Magic TCG to refrain from using AI generative tools to create final Magic products. We work with some of the most talented artists and creatives in the world, and we believe those people are what makes Magic great.
Imagine AI generating an entire deck of Magic cards (art and text), with mechanics from scratch and everything. It’d play like shit, but might be fun for the laughs of trying to figure out what was going on.
Actually, I wonder if it could just figure out a deck just using existing cards and mechanics. Could an AI actually work out a really good combo deck where all the cards just work together or find relationships and synergies?
cardmarket did a few videos where they played with ai generated cards. it was really funny and they did not play well at all. it was also a billion ai years ago (2022) so the models have gotten more powerful since then
deleted by creator
If it’s anything like the DnD results I’ve gotten it’s the blandest most generic thing you will see. So most likely a deck of the most common cards or a weird hybrid between two good decks that are terrible. Might be fun as a challenge to see if you can get it work at all
@dumples @MysticKetchup @paddirn yeah, the computer doesn’t understand strategy or niche interactions. Most “AI” right now is just really good at averaging. So yeah, if you’d like an average deck that fits your requirements, it might do that. But it’s probably only really playable for agro decks because they have the most straightforward strategy.
Reminds me of that Twitter bot roborosewater
You could totally have that and it wouldn’t need to play like shit at all.
What you’d want to do is pair up a few different layers of AI.
The base layer would be a fine tuned LLM describing card mechanics, flavor text, and art. You’d use this to generate a ton of synthetic cards for each color deck, ideally directing it using manual prompt controls to create a mix representative of actual frequencies of various costs and types so you have a sample that will pace well with typical game play.
Then you’d need a model that plays Magic adeptly according to the rules, which should be able to be accomplished with something like AlphaZero, an approach that works really well for learning games.
You’d gradually advance that second model from playing well with premade decks to picking its own deck from legal cards until it was able to beat versions of itself using competition winning decks.
Then you gradually start mixing in your synthetic cards, removing less used legal cards as you go until you finally have added all synthetic cards and have no legal cards.
Then you reduce the synthetic cards to the most used X number of cards for each color or mixed color decks being built by the competitive AI.
Finally, you have a set of AI generated cards that would likely be pretty fun to play.
While right now that’s a pretty expensive and labor intensive process, within the decade it’s the kind of thing you’d be able to set up in a weekend on local hardware as long as you have a digital copy of all legal Magic cards in a standardized text format and competition deck records in the same.