AI RESEARCH
GPT-Image-2 in the Wild: A Twitter Dataset of Self-Reported AI-Generated Images from the First Week of Deployment
arXiv CS.CV
•
ArXi:2604.25370v1 Announce Type: new The release of GPT-image-2 by OpenAI marks a watershed moment in AI-generated imagery: the boundary between photographic reality and synthetic content has never been difficult to discern. We We characterize the dataset across four analyses: CLIP-based zero-shot subject taxonomy, OCR text legibility (82.0% of images contain detectable text), face detection (59.2% of images, 22,583 total faces), and semantic clustering (137 CLIP ViT-L/14 clusters