Sakana AI's self-improving model gets better at solving and judging, but can't catch its own blind spots

Sakana AI's MASS method allows a language model to improve itself by solving tasks, judging results, and refining workflows, achieving a win rate of nearly 70 percent against the base model after two rounds. However, when the model misses the same errors across all three roles, it can mistake them for progress and reinforce them during training.