Humans aren't exactly great at this either; cards needing to be banned has only gotten more frequent over time, although it looks like this year has been the first one in a while not to require a lot[1]
I'd argue that humans are actually pretty fucking good at this. After all, it's humans who are exploiting the weaknesses WOTC build into the game via new card releases. Balance testing is a numbers game though. If you test your software you can be reasonably confident if you release it to 10 people, it'll perform pretty much as expected. If that software is installed by millions of people, you're going to start experiencing every edge case that can only occur in extremely rare circumstances.
Or another example, the software released to ten customers can be insecure with little repercussions. But insecure software released to millions is going to be zero-day'd in no time. The MTG community absolutely has hackers that are just waiting for the latest vulnerability to be released.
The latest set released by WOTC this week has an infinite mana loop that you can get on turn four. I don't think this stuff will ever stop, and I honestly hope it doesn't. Bans / restrictions can mitigate the damage to certain formats, and it really stirs up the creativity of folks in the meantime.
There has been a paper on using genetic algorithms for deckbuilding in magic[0]
I'm working on at least partially reproducing and improving upon the paper but the reality is that MTG as a game is really hard to implement (and a shitload of work) so i'm building my own MTG inspired game to try and balance it using genetic deck building.
You’d expect that to happen as potential interactions increase, I assume. I’ve always wanted to learn how to use a modelling tool like TLA+ or something to find breaking issues in games - like first turn wins (that isn’t just Exodia in Yugioh)
I can see them using it in a purely creative context, like generating a bunch of cards and then looking for novel and interesting cards you wouldn't have otherwise though of. But designing cards is fun for a human to do and not terribly hard, so I don't think we'll see entire sets generated by AI, or even an entire card generated by AI that a human doesn't go back and balance numbers on or fine tune a mechanic.
Considering the amount of cards they tend to produce these days, makes you wonder if they aren't already using some kind of AI to generate a baseline of cards.
It would be interesting if it could make balanced cards. I wonder what kind of crazy op decks these generated cards allows for
Humans aren't exactly great at this either; cards needing to be banned has only gotten more frequent over time, although it looks like this year has been the first one in a while not to require a lot[1]
[1]: https://mtg.fandom.com/wiki/Banned_and_restricted_cards/Time...
I'd argue that humans are actually pretty fucking good at this. After all, it's humans who are exploiting the weaknesses WOTC build into the game via new card releases. Balance testing is a numbers game though. If you test your software you can be reasonably confident if you release it to 10 people, it'll perform pretty much as expected. If that software is installed by millions of people, you're going to start experiencing every edge case that can only occur in extremely rare circumstances.
Or another example, the software released to ten customers can be insecure with little repercussions. But insecure software released to millions is going to be zero-day'd in no time. The MTG community absolutely has hackers that are just waiting for the latest vulnerability to be released.
The latest set released by WOTC this week has an infinite mana loop that you can get on turn four. I don't think this stuff will ever stop, and I honestly hope it doesn't. Bans / restrictions can mitigate the damage to certain formats, and it really stirs up the creativity of folks in the meantime.
3 replies →
There has been a paper on using genetic algorithms for deckbuilding in magic[0]
I'm working on at least partially reproducing and improving upon the paper but the reality is that MTG as a game is really hard to implement (and a shitload of work) so i'm building my own MTG inspired game to try and balance it using genetic deck building.
[0] https://ntnuopen.ntnu.no/ntnu-xmlui/bitstream/handle/11250/2...
2 replies →
You’d expect that to happen as potential interactions increase, I assume. I’ve always wanted to learn how to use a modelling tool like TLA+ or something to find breaking issues in games - like first turn wins (that isn’t just Exodia in Yugioh)
2 replies →
I am extremely confident WoTC is aware of this and is working on and/or using similar
I can see them using it in a purely creative context, like generating a bunch of cards and then looking for novel and interesting cards you wouldn't have otherwise though of. But designing cards is fun for a human to do and not terribly hard, so I don't think we'll see entire sets generated by AI, or even an entire card generated by AI that a human doesn't go back and balance numbers on or fine tune a mechanic.
Considering the amount of cards they tend to produce these days, makes you wonder if they aren't already using some kind of AI to generate a baseline of cards.