#hypertext

Multiverse Writing

Multiverse Writing

Language models like GPT-3 have advanced to a level where they can work together with humans to write content. In a recent article, two authors propose to use these tools for writing and reading in nonlinear ways.

They suggest creating interfaces that allow humans to collaborate with AI to generate and understand nonlinear stories. The authors share their experiences developing and testing a new writing interface that uses GPT-3 to help writers create what they call “multiverse stories.”

We propose the creation of new tools to allow writers to work alongside language models to explore and be inspired by the multiverses already hiding in their writing. […] An effective multiversal interface should allow the writer, with the aid of a generative language model, to expose, explore, and exploit the interpretational and dynamic multiplicity of a passage. Not only will such a tool allow the user to explore the ways in which a scenario might play out, such an interface will also expose previously unnoticed ambiguities in the text (and their consequences). Depending on the design of the interface and the way the user approaches it, many different human-AI collaborative workflows are possible. Ideally, the interface should give the user a sense of creative superpowers, providing endless inspiration combined with executive control over the narrative, as well as allowing and encouraging the user to intervene to any degree.

The article, entitled “ Multiversal views on language models ” is written by Laria Reynolds and Kyle McDonell.

Accompanying the article, on GitHub, there is an app called “ Loom: An interface to generate, navigate, and visualize natural language multiverses

A related blog post describes the motivation behind Loom .

AI Dungeon has several features helpful for writing longform works, such as pinned memory, World Info, and automatic summarization. However, it is missing support for a feature which I’ve found to be a great power multiplier for co-writing with language models: branching. Adventures on AI Dungeon are single-history: you can edit actions and retry generation, but only one variation can be saved to the adventure. You can get around this by duplicating the adventure, but there’s no representation of the fact that the copies are forked from the same point, so branching more than a few times leads to a confusing profusion of adventures. […] I use the loom for all my GPT-3-assisted writing, as well as for brainstorming and prototyping prompts. I created it for personal use, so the interface hasn’t been made user-friendly and lacks documentation (this doesn’t count). However, anyone with an OpenAI API key is welcome to beta test it.