I think a non-LLM model would be good for learning to draft within a particular set, because it can simply encode each card and learn what cards do well together, comparative strength, etc. without learning the stats/rules text on the card.
For learning to draft in one environment and then applying it to a new set of cards, like done here, it would become far more difficult to do without an LLM. The variations and nuances of cards rules text would have to be encoded as features, which would be extremely cumbersome. The LLM gets you some level of understanding of that for free.
Fair and valid points, it’s been years since I played magic but I agree an LLM would Be very useful in reading the cards and possibly then getting into understanding strategy based on that context.
For learning to draft in one environment and then applying it to a new set of cards, like done here, it would become far more difficult to do without an LLM. The variations and nuances of cards rules text would have to be encoded as features, which would be extremely cumbersome. The LLM gets you some level of understanding of that for free.