MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) ... identified a phenomenon they call attribution decay, where the more data a generative model is trained on, the less any individual training example matters to any particular output. It feels counterintuitive, but at sufficiently large scales, they find, you can often remove any single image from the training data, or every image by a given artist, or every photograph of a given person, and the generated sample doesn't change. And if removing something changes nothing, the researchers argue, it can't be said to be responsible for anything. ... Their workaround is...