Strategic Behavior and AI Training Data

Christian Peukert, Florian Abeillon, Jérémie Haese, Franziska Kaiser and Alexander Staub

No 11099, CESifo Working Paper Series from CESifo

Abstract: Human-created works represent critical data inputs to artificial intelligence (AI). Strategic behaviour can play a major role for AI training datasets, be it in limiting access to existing works or in deciding which types of new works to create or whether to create new works at all. We examine creators’ behavioral change when their works become training data for AI. Specifically, we focus on contributors on Unsplash, a popular stock image platform with about 6 million high-quality photos and illustrations. In the summer of 2020, Unsplash launched an AI research program by releasing a dataset of 25,000 images for commercial use. We study contributors’ reactions, comparing contributors whose works were included in this dataset to contributors whose works were not included. Our results suggest that treated contributors left the platform at a higher-than-usual rate and substantially slowed down the rate of new uploads. Professional and more successful photographers react stronger than amateurs and less successful photographers. We also show that affected users changed the variety and novelty of contributions to the platform, with long-run implications for the stock of works potentially available for AI training. Taken together, our findings highlight the trade-off between interests of rightsholders and promoting innovation at the technological frontier. We discuss implications for copyright and AI policy.

Keywords: generative artificial intelligence; training data; licensing; copyright; natural experiment (search for similar items in EconPapers)
JEL-codes: K11 L82 L86 (search for similar items in EconPapers)
Date: 2024
New Economics Papers: this item is included in nep-big, nep-cmp and nep-tid
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
https://www.cesifo.org/DocDL/cesifo1_wp11099.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ces:ceswps:_11099

Access Statistics for this paper

More papers in CESifo Working Paper Series from CESifo Contact information at EDIRC.
Bibliographic data for series maintained by Klaus Wohlrabe ().