Vision models heavily rely on fine-tuning general-purpose models pre-trained on large, static datasets. These general-purpose models only understand knowledge within their pre-training datasets, which are tiny, out-of-date snapshots of the Internet—where billions of images are uploaded each day. We suggest an alternate approach: rather than training one large general-purpose model, we propose dynamically utilizing the Internet to quickly train a small-scale model that does extremely well on a ta…