Sakana AI 推出 MASS 自我改进方法，两轮后胜率达 70%
Sakana AI's self-improving model gets better at solving and judging, but can't catch its own blind spots
Sakana AI 让一个模型自己解题自己批改，两轮后对原版胜率近 70%，不过文章也讲清了这种自我改进什么时候会把错误越练越深。
Sakana AI 提出 MASS 方法，让一个语言模型同时承担解题、评判和改进工作流三个角色，实现自我迭代。经过两轮自我改进后，改进版模型对基础模型的胜率接近 70%。但该方法存在盲区：当模型在解题、评判和改进三个角色中犯下相同错误时，训练会把错误当作进步予以强化。
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 lets one language model improve itself by solving tasks, judging results, and refining workflows, reaching a win rate of nearly 70 percent against the base model after two rounds. But when the model misses the same errors across all three roles, it can mistake them for progress and reinforce them during training. The article Sakana AI's self-improving model gets better at solving and judging, but can't catch its own blind spots appeared first on The Decoder .
