Multiversal views on language models
This work addresses the challenge of enhancing creative writing through AI interfaces, but it is incremental as it builds on existing language models without major methodological breakthroughs.
The paper tackles the problem of human-AI collaboration in writing by conceptualizing language models as multiverse generators, resulting in the development and testing of a novel GPT-3-assisted writing interface for non-linear fiction.
The virtuosity of language models like GPT-3 opens a new world of possibility for human-AI collaboration in writing. In this paper, we present a framework in which generative language models are conceptualized as multiverse generators. This framework also applies to human imagination and is core to how we read and write fiction. We call for exploration into this commonality through new forms of interfaces which allow humans to couple their imagination to AI to write, explore, and understand non-linear fiction. We discuss the early insights we have gained from actively pursuing this approach by developing and testing a novel multiversal GPT-3-assisted writing interface.