Collectible card games (CCGs) are a difficult genre for AI due to their partial observability, long-term decision-making, and evolving card sets. Due to this, current AI models perform vastly worse than human players at CCG tasks such as deckbuilding and gameplay. In this work, we introduce UrzaGPT, a domain-adapted large language model that recommends real-time drafting decisions in Magic: The Gathering. Starting from an open-weight LLM, we use Low-Rank Adaptation fine-tuning on a dataset of annotated draft logs. With this, we leverage the language modeling capabilities of LLM, and can quickly adapt to different expansions of the game. We benchmark UrzaGPT in comparison to zero-shot LLMs and the state-of-the-art domain-specific model. Untuned, small LLMs like Llama-3-8B are completely unable to draft, but the larger GPT-4o achieves a zero-shot performance of 43%. Using UrzaGPT to fine-tune smaller models, we achieve an accuracy of 66.2% using only 10,000 steps. Despite this not reaching the capability of domain-specific models, we show that solely using LLMs to draft is possible and conclude that using LLMs can enable performant, general, and update-friendly drafting AIs in the future.

This paper examines the role that enchantment plays in the design of AI things by constructing a taxonomy of design approaches that increase or decrease the perception of magic and enchantment. We start from the design discourse surrounding recent developments in AI technologies, highlighting specific interaction qualities such as algorithmic uncertainties and errors and articulating relations to the rhetoric of magic and supernatural thinking. Through analyzing and reflecting upon 52 students' design projects from two editions of a Master course in design and AI, we identify seven design principles and unpack the effects of each in terms of enchantment and disenchantment. We conclude by articulating ways in which this taxonomy can be approached and appropriated by design/HCI practitioners, especially to support exploration and reflexivity.

Once upon a time, when it was still of some use to wish for what one wanted… …there lived a King and Queen who had a daughter who was lovely to behold but who never laughed, or perhaps, …there lived an old fisherman by the side of a sea that had hardly any fishes in it. If you are like me, you are already hooked. In the many stories of the three magic wishes, promises of infinite riches are just for the asking, but the wishes are always spent, first on foolishness, second on disaster, and third on bare recovery. In the Monkey's Paw, the old couple's first wish is for 200 pounds. The second wish is the return of their just-killed son.

Projects Visualizing Targeted Audiences Users of social networks can be passionate about sharing their political convictions, art projects, or business ventures. They often want to direct their social interactions to certain people in order to start collaborations or to raise awareness about issues they support. However, users generally have scattered, unstructured information about the characteristics of their audiences, making it difficult for them to deliver the right messages or interactions to the right people. Existing audience-targeting tools allow people to select potential candidates based on predefined lists, but the tools provide few insights about whether or not these people would be appropriate for a specific type of communication. We introduce an online tool, \textit{Hax}, to explore instead the idea of using interactive data visualizations to help people dynamically identify audiences for their different sharing efforts.

Indeed, this is true, if for no attraction reaches almost all of us. Fairy stories let us enter an enchanted world. We do Magic abounds, though always in special ways. Villainy is there, certainly danger. We need the hidden guidance of The spell is broken, and the Princess smiles and fairy stories to tell us of the trials we must marries the youth who made her laugh.