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

**Published:** October 12, 2026
**Author:** Jonathan Kemper
**Source:** The Decoder
**Language:** en-US
**HTML:** https://aiqazaqstan.com/en/articles/sakana-ai-s-self-improving-model-gets-better-at-solving-and-judging-but

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…

> From the original source: **The Decoder**
> [Read full article at The Decoder](https://the-decoder.com/sakana-ais-self-improving-model-gets-better-at-solving-and-judging-but-cant-catch-its-own-blind-spots/)

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*