Large-scale analysis of wild LLM chat logs finds that user interaction patterns stabilize quickly after initial use and correlate with long-term outcomes like retention, creating an agency paradox of limited exploration in unconstrained systems.
Mathewson, Jaylen Pittman, and Richard Evans
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 4roles
background 2representative citing papers
TombWriter scaffolds story archeology via beat-level human-AI interaction in a five-stage pipeline, with qualitative findings from five writers indicating value for structural discovery over prose generation.
Higher generative AI error rates reduce user reliance, but task difficulty does not significantly moderate this effect.
citing papers explorer
-
Priming, Path-dependence, and Plasticity: Understanding the molding of user-LLM interaction and its implications from (many) chat logs in the wild
Large-scale analysis of wild LLM chat logs finds that user interaction patterns stabilize quickly after initial use and correlate with long-term outcomes like retention, creating an agency paradox of limited exploration in unconstrained systems.
-
Effects of Generative AI Errors on User Reliance Across Task Difficulty
Higher generative AI error rates reduce user reliance, but task difficulty does not significantly moderate this effect.