SAGA: Collaborative Storytelling with GPT-3
Bibliographic record
Abstract
When friends live across different time zones, have incompatible work schedules, or have different levels of access to technology, synchronous communication becomes infeasible. To address this challenge, we developed a web application that allows friends to asynchronously collaborate creatively. In this application, multiple people can contribute to the writing of a story, told partially by a natural language AI system. By offloading some of the creative work to the AI, the human writers have the opportunity to also act as readers, being surprised by new events in the story. To gain preliminary insights into the experience of using this system, we conducted an informal pilot study over a span of 5 days. Through this process, we learned that storytelling with an AI system can encourage roleplay, it can be a cathartic experience, and it is curiosity-driven. Our recommendations for future research include (1) investigating new turn-taking strategies, and clearly communicating turns through the interface, (2) providing guidance for the prompt-writing process, perhaps through editable prompt templates, and (3) conducting a thorough evaluation of the system with friend groups of various sizes and timezones.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.002 | 0.004 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.029 | 0.007 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".