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

Researchers from Sakana AI and UC Berkeley have introduced "Multi-Agent Self-Supervision" (MASS), a recursive self-improvement method where a single language model solves tasks, refines workflows, and judges results. While achieving a win rate of nearly 70 percent against the base model after two ro

Hírek

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