# Next Token Prediction Is a Dead End for Creativity

arXiv: https://arxiv.org/abs/2505.19277 · HTML: https://mlsanity.com/paper/2505.19277/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 33 references that are in the map.
- First posted on arXiv 25 May 2025.

## Builds on (most cited first, 3 of 3)

- [PaperBench: Evaluating AI's Ability to Replicate AI Research](https://mlsanity.com/paper/2504.01848/) (2025)
- [The Lovelace 2.0 Test of Artificial Creativity and Intelligence](https://mlsanity.com/paper/1410.6142/) (2014)
- [A Call for Clarity in Beam Search: How It Works and When It Stops](https://mlsanity.com/paper/2204.05424/) (2022)

## Abstract (arXiv)

This paper argues that token prediction is fundamentally misaligned with real creativity. While next-token models have enabled impressive advances in language generation, their architecture favours surface-level coherence over spontaneity, originality, and improvisational risk. We use battle rap as a case study to expose the limitations of predictive systems, demonstrating that they cannot truly engage in adversarial or emotionally resonant exchanges. By reframing creativity as an interactive process rather than a predictive output, we offer a vision for AI systems that are more expressive, responsive, and aligned with human creative practice.