Max Kreminski

Me in my workspace.

Ph.D. Candidate, Computational Media

Expressive Intelligence Studio

University of California, Santa Cruz

Pronouns: they/them

About

I’m a late-stage Computational Media Ph.D. candidate in the Expressive Intelligence Studio at the University of California, Santa Cruz. I build computational systems that engage in expressive reasoning to help people frame and solve complex design problems, especially in the domains of narrative and game design. My research aims to offload the painful and tedious parts of creative work onto the computer, empowering diverse users to create expressive artifacts (particularly games and stories) that push the boundaries of human expressive potential.

Broadly speaking, my research interests include artificial intelligence, human-computer interaction, interactive narrative, generative methods, computational creativity, and games. For a complete list of my publications, talks, and other academic output, see my CV.

Intelligent narrative technologies

Visualization of a pool of partial Winnow sifting pattern matches evolving as new events take place.
Winnow is a human-friendly domain-specific language for writing story sifting patterns. It provides unique affordances for incremental story sifting, enabling the computer to detect emergent microstories while they’re still playing out.
System diagram of Why Are We Like This?, showing how the system suggests what should happen next in response to player actions.
Why Are We Like This? is an in-development AI-augmented collaborative storytelling game. Two players write a story in a pastiche of the cozy mystery genre, with support from a simulation-based AI system that suggests what might happen next based on both character and authorial goals.
Screenshot of Synthesifter’s user interface, synthesizing a sifting pattern that matches a sequence of two romantic failures followed by a romantic success.
Synthesifter is a graphical authoring tool that uses inductive logic programming to help users write story sifting patterns. Users specify concrete positive and negative examples of the kinds of microstories they want to match, and the system interactively synthesizes a Felt sifting pattern that meets their requirements.
Partial example of a Felt sifting pattern that matches a sequence of events involving two impulsive betrayals.
Felt is a simple story sifting and simulation engine for emergent narrative play experiences. It provides narrative system developers with tools for defining story sifting patterns that match narratively potent sequences of events, and for building simulations in which characters make use of story sifting to reason about the world.
System diagram of StoryAssembler, showing how execution co-routines between a forward state-space planner and hierarchical task network planner.
StoryAssembler is an interactive narrative system that assembles choice-based stories on the fly from a library of author-provided story fragments, using planning to ensure that every story it produces meets a set of author-specified requirements.
Partial screenshot of codebook that notes dimensions of variation between Civilization VI and Stellaris retellings, from the AIIDE 2019 paper linked below.
Retellings studies are a series of investigations into the stories that players tell about their experiences in games, especially simulation-driven emergent narrative games. This work helps us better understand how to provide computational support for human storytelling practices.

Computational support for game design

Screenshot of the Germinate user interface, showing a design intent on the left and a generated game on the right.
Germinate is a mixed-initiative casual creator for rhetorical game design, built on the Gemini game generator. It generates games based on a user-provided design intent, then provides users with support in exploring the resulting design space and refining their intent based on the generated games.
System diagram of a single generated Game Boy RPG.
GBS is a genre-specific game description language for Game Boy RPGs, extracted from the GB Studio game creation tool. We’re using it as a shared language between human designers and computational systems to build an ecosystem of game design support tools that better understand games as an expressive medium.

Other selected projects

Screenshot of the Blabrecs AI testing the nonsense word “torbible” and saying “looks good to me!”
Blabrecs is a rules modification for the wordgame Scrabble that forbids players from using actual English dictionary words. Instead, players may only use nonsense words that sound like English to an AI trained on the dictionary.
Screenshot of an Academical scene in which an aging hippie professor discusses an ethical dilemma with a grad student.
Academical is an interactive narrative game that uses roleplaying to train new researchers in responsible conduct of research. Our user studies have found that Academical is better than existing RCR training materials at engaging users, teaching some RCR topics, and promoting moral reasoning, without falling behind in other areas.
A two-line poem created using Redactionist: “the mission is the infinite variability / that poetry can speak”.
Redactionist is an AI-based tool that helps you create poetry by erasing words from a source text. It builds on my earlier work in this direction: a browser bookmarklet that can turn any arbitrary webpage into blackout poetry.
Screenshot of Epitaph, showing a procedurally generated alien civilization called the Gep.
Epitaph is a procedural narrative idlegame about existential risks and the death of civilizations. Bennett Foddy (the creator of QWOP) considers it “one of the great web games”. It was the precursor to my academic work on gardening games, which use procedural content generation to support gameplay experiences of caretaking rather than extraction.