Throwing Bottles at God: Predictive Text as a Game Mechanic in an AI-Based Narrative Game

Kreminski, Max; Wardrip‐Fruin, Noah

doi:10.1007/978-3-030-04028-4_29

Search citation statements

Order By: Relevance

Paper Sections

Select...

Related Work1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2021

Publication Types

Select...

Article1

Book1

Relationship

Self Cite0

Independent2

Authors

Journals

Cited by 2 publications

(1 citation statement)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the first author's previous AI-based game projects-Throwing Bottles at God (Kreminski and Wardrip-Fruin 2018)-represents an earlier attempt to make Markov chains playable. Rather than classifying playersubmitted text, Throwing Bottles makes use of Markov chains as a predictive text algorithm to help the player write short messages in a particular style; this can be viewed in hindsight as a failed experiment, whereas Blabrecs has been much more successful in eliciting the desired player experience.…”

Section: Related Workmentioning

confidence: 99%

A Demonstration of Blabrecs, an AI-Based Wordgame

Kreminski

Karth

2021

AIIDE

View full text Add to dashboard Cite

Blabrecs is an AI-based modification to the popular wordgame Scrabble. In Blabrecs, English dictionary words may not be played; instead, players may only play nonsense words that are approved by a classifier trained on a list of English dictionary words. Gameplay therefore revolves around inventing plausibly English-sounding nonsense words and learning how to fool the classifier. In this paper, we briefly introduce our design goals for Blabrecs; describe the process by which Blabrecs was designed; and present two distinct implementations of the game's AI judge.

show abstract

Section: Related Workmentioning

confidence: 99%