“Our primary conclusion across all scenarios is that without enough fresh real data in each generation of an autophagous loop, future generative models are doomed to have their quality (precision) or diversity (recall) progressively decrease,” they added. “We term this condition Model Autophagy Disorder (MAD).”
Interestingly, this might be a more challenging problem as we increase the use of generative AI models online.
I only have a small amount of experience with generating images using AI models, but I have found this to be true. It’s like making a photocopy of a photocopy. The results can be unintentionally hilarious though.
If you let the AI feed on its own bullshit long enough it will eventually vote for Donald Trump
So we have generation loss instead of AI making better AI. At least for now. That’s strangely comforting.
Its like making a photocopy of a photocopy.
