Multiversal views on language models

TL;DR

This paper introduces a multiversal framework for understanding language models like GPT-3, emphasizing their role in human-AI collaborative fiction writing and proposing new interfaces to explore this potential.

Contribution

It conceptualizes language models as multiverse generators and develops a novel GPT-3-assisted writing interface for non-linear fiction exploration.

Findings

Early insights from testing the multiversal GPT-3 writing interface

Potential for new human-AI collaborative storytelling methods

Framework linking language models, imagination, and fiction

Abstract

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.