Mapping Mixed-Initiative Creative Interfaces: How Can Humans and AI Collaborate in Creative Practice?

As part of the current bloom of artificial intelligence, we are seeing the rise of ‘creative AI’ – artificial intelligence that produces or supports creative work like making games, writing prose, composing music, or editing films. 

A particularly novel and interesting approach in this field are so-called Mixed-Initiative Creative Interfaces or MICIs (Deterding et al., 2017). Rather than human creators using computers as a tool, or computers acting as creators on their own, in MICIs, human and AI engage in a creative dialogue, taking turns constraining, suggesting, producing, modifying, selecting, and evaluating creative outputs. One example is TANAGRA, where a human game designer suggests a rough draft of a game level, and the AI produces a detailed game map, automatically analyses whether the map is actually playable, and if not, suggests edits. 

The goal of this project is to understand the different ways in how humans and AI can collaborate in a creative endeavor. The project will build on a very successful MICI mapping project undertaken by DC Labs summer school students in 2017. Since this time, the creative AI space has exploded, and this project will help us capture these new developments.

Using standard classifications for creative practices (framing, ideating, selecting, assessing, modifying, ...), you will collect existing MICI systems across domains (games, visual art, ...) and build visualisations showing which kinds of collaboration have been realised in which domains and which therefore remain underexplored. 

To do so, you will:

  • learn to do a systematic literature review on MICIs;
  • build a taxonomy or map of all discovered MICIs;
  • revise a database containing a first mapping of MICIs: http://mici.codingconduct.cc/
  • visualize database results

Required Skills

We are seeking candidates for two roles, with the following spread of skills:

Required Skills

How to Apply

For more details on the summer school application process (including eligibility and funding) please go here: https://digitalcreativity.ac.uk/news/dc-labs-summer-school-2021 

If you would like to ask any informal questions about the research project, please contact Prof Sebastian Deterding sebastian.deterding@york.ac.uk and Dr Joe Cutting joe.cutting@york.ac.uk 

For questions about the programme, logistics etc, please contact Ella Eyre, DC Labs Administrator, on enquiries@digitalcreativity.ac.uk 

Supervisors

Professor Sebastian Deterding, Department of Theatre, Film, Television and Interactive Media

Dr. Jonathan Hook, Department of Theatre, Film, Television and Interactive Media

Dr. Florian Block, Department of Theatre, Film, Television and Interactive Media

Dr. Joe Cutting, Department of Theatre, Film, Television and Interactive Media

Further Reading

Deterding, C. S., Hook, J. D., Fiebrink, R., Gow, J., Akten, M., Smith, G., ... & Compton, K. (2017). Mixed-Initiative Creative Interfaces. In Proceedings of CHI 2017 Extended Abstracts. ACM. https://dl.acm.org/doi/abs/10.1145/3027063.3027072