Although directive prompting is the predominant way to interact with Large Language Models (LLMs), many creative practices rely on language that is open-ended, associative, phonaesthetic, symbolic, and that unfolds across multiple temporalities. In this work, we explore how creative practitioners might work with AI systems when language is treated not merely as instruction but as material. We conducted an ecological two-week study with four creative practitioners using a design probe: the Memetic Mixer, a tangible interactive device that constrains interaction with an LLM. Analysis of post-study interviews and device logs identified distinct modes of material language use and temporalities that shaped each participant’s engagement with AI and their creative practice. We reflect on these findings and contribute design considerations that support open-ended interaction with AI in creative practice.

Recent advances in generative AI music have resulted in new technologies that are being framed as co-creative tools for musicians with early work demonstrating their potential to add to music practice. While the field has seen many valuable contributions, work that involves practising musicians in the design and development of these tools is limited, with the majority of work including them only once a tool has been developed. In this paper, we present a case study that explores the needs of practising musicians through the co-design of a musical variation system, highlighting the importance of involving a diverse range of musicians throughout the design process and uncovering various design insights. This was achieved through two workshops and a two week ecological evaluation, where musicians from different musical backgrounds offered valuable insights not only on a musical system's design but also on how a musical AI could be integrated into their musical practices.

Recent developments in prompt-based generative AI has given rise to discourse surrounding the perceived ethical concerns, economic implications, and consequences for the future of cultural production. As generative imagery becomes pervasive in mainstream society, dominated primarily by emerging industry leaders, we encourage that the role of the CHI community be one of inquiry; to investigate the numerous ways in which generative AI has the potential to, and already is, augmenting human creativity. In this paper, we conducted a diffractive analysis exploring the potential role of prompt-based interfaces in artists’ creative practice. Over a two week period, seven visual artists were given access to a personalised instance of Stable Diffusion, fine-tuned on a dataset of their work. In the following diffractive analysis, we identified two dominant modes adopted by participants, AI for ideation, and AI for production. We furthermore present a number of ethical design considerations for the future development of generative AI interfaces.

Creative computing is an approach to computing education which emphasises the creation of interactive audiovisual software and an art-school influenced pedagogy. Given this emphasis on Dewey's "learning by doing", we set out to investigate the processes students use to develop their programs. We refer to these processes as the students' 'coding behaviour', and we expect that understanding it will provide us with valuable information about how students learn in our creative computing classes. As existing metrics were not sufficient, we introduce a new set of quantitative metrics to describe coding behaviours. The metrics consider factors such as students' vocabulary use and development, how fast and how much they alter the functionality of code over time and how they iterate on their code through text insert and delete operations. Many of our lessons involve providing students with demonstrator code which they use as a base for the development of their programs, so we use demo code as an entry point to our dataset. We look at programs students have written through developing the demo code in a dataset of over 16,000 programs. We clustered the demo code using the set of descriptive metrics. This lead to a set of clusters containing programs which are associated with distinct coding behaviours. Four was the ideal number of clusters for cluster density and separation. We found that the clusters had distinct behaviour patterns, that they were associated with different instructors and that they contained demo programs with different lengths.

Collaboration is built on trust, and establishing trust with a creative Artificial Intelligence is difficult when the decision process or internal state driving its behaviour isn't exposed. When human musicians improvise together, a number of extra-musical cues are used to augment musical communication and expose mental or emotional states which affect musical decisions and the effectiveness of the collaboration. We developed a collaborative improvising AI drummer that communicates its confidence through an emoticon-based visualisation. The AI was trained on musical performance data, as well as real-time skin conductance, of musicians improvising with professional drummers, exposing both musical and extra-musical cues to inform its generative process. Uni- and bi-directional extra-musical communication with real and false values were tested by experienced improvising musicians. Each condition was evaluated using the FSS-2 questionnaire, as a proxy for musical engagement. The results show a positive correlation between extra-musical communication of machine internal state and human musical engagement.

Abstract Refinement is a powerful mechanism for mastering the complexities that arise when formally modelling systems. Refinement also brings with it additional proof obligations—requiring a developer to discover properties relating to their design decisions. With the goal of reducing this burden, we have investigated how a general purpose automated theory formation tool, HR, can be used to automate the discovery of such properties within the context of the Event-B formal modelling framework. This gave rise to an integrated approach to automated invariant discovery. In addition to formal modelling and automated theory formation, our approach relies upon the simulation of system models as a key input to the invariant discovery process. Moreover we have developed a set of heuristics which, when coupled with automated proof-failure analysis, have enabled us to effectively tailor HR to the needs of Event-B developments. Drawing in part upon case study material from the literature, we have achieved some promising experimental results. While our focus has been on Event-B, we believe that our approach could be applied more widely to formal modelling frameworks which support simulation.

Nowadays, the detection and correction of software defects has become a very hard task for software engineers. Most importantly, the lack of standard specifications of these software defects along with the lack of tools for their detection, correction and verification forces developers to perform manual modifications; resulting not only in mistakes, but also in costs of time and resources. The work presented here is a study of the specification and correction of a particular type of software defect: Object-Oriented anti-patterns. More specifically, we define a UML based specification of anti-patterns and establish design transformations for their correction. Through this work, we expect to open up the possibility to automate the detection and correction of these kinds of software defects.