Describing a situation much like the dangers of genetic inbreeding, computer scientists Matyas Bohacek and Hany Farid wrote a paper that describes how AI image generators that start training with their own generated data quickly start deteriorating.

‘Nepotistically Trained Generative-AI Models Collapse‘ shows that training an AI image generator on AI generated images quickly leads to a deterioration in the quality of output which can only be fixed by re-introducing real images.

In Nature, a more recent study found a similar effect in text generation, with the use of synthetic data leading to increasingly nonsensical results.

Artifactory:

• https://arxiv.org/abs/2311.12202
• https://www.creativebloq.com/ai/ai-art/research-shows-ai-image-generators-could-be-their-own-demise