Sakana's MASS self-improving model reaches ~70% win rate but misses blind spots

Sakana AI's MASS method has one language model improve itself by solving tasks, judging results, and refining workflows. After two rounds it won nearly 70 percent against the base model. When the model misses the same errors in all three roles, it can mistake them for progress and reinforce them in training.

Why it matters: Self-improvement loops where the same model judges its own work have a correlated-error ceiling: shared blind spots look like success. This echoes the agent-overstating-results findings and argues for independent verifiers in any recursive-improvement pipeline.