Can you imagine the regulatory mess once AI cracks Continual Learning? Right now, model weights are mostly fixed after training; you can fine-tune, patch, and steer the system afterward, but the core model is still treated as a relatively stable artifact. With Continual Learning, that assumption breaks, as models may keep modifying their weights, absorbing new information, and developing new capabilities after deployment. So how do you "test" such a model for capabilities? You don’t certify a thing anymore, you chase a moving target, and that quickly turns into a never-ending cat-and-mouse game between regulators and models that keep changing. Continual Learning is definitely coming, and it's not too far away.