{"slug": "sakana-ai-s-self-improving-model-gets-better-at-solving-and-judging-but-can-t", "title": "Sakana AI's self-improving model gets better at solving and judging, but can't catch its own blind spots", "summary": "Sakana AI's MASS method, which lets a single language model improve itself by solving tasks, judging results, and refining workflows, reached a win rate of nearly 70 percent against the base model after two rounds, The Decoder reported. The method fails when the model makes the same errors across all three roles, causing it to mistake those errors for progress and reinforce them during training.", "body_md": "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.\n\nThe article [Sakana AI's self-improving model gets better at solving and judging, but can't catch its own blind spots](https://the-decoder.com/sakana-ais-self-improving-model-gets-better-at-solving-and-judging-but-cant-catch-its-own-blind-spots/) appeared first on [The Decoder](https://the-decoder.com).", "url": "https://wpnews.pro/news/sakana-ai-s-self-improving-model-gets-better-at-solving-and-judging-but-can-t", "canonical_source": "https://the-decoder.com/sakana-ais-self-improving-model-gets-better-at-solving-and-judging-but-cant-catch-its-own-blind-spots/", "published_at": "2026-10-12 17:58:54+00:00", "updated_at": "2026-10-12 18:20:15.116541+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-research", "ai-safety"], "entities": ["Sakana AI", "MASS", "The Decoder"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/sakana-ai-s-self-improving-model-gets-better-at-solving-and-judging-but-can-t", "markdown": "https://wpnews.pro/news/sakana-ai-s-self-improving-model-gets-better-at-solving-and-judging-but-can-t.md", "text": "https://wpnews.pro/news/sakana-ai-s-self-improving-model-gets-better-at-solving-and-judging-but-can-t.txt", "jsonld": "https://wpnews.pro/news/sakana-ai-s-self-improving-model-gets-better-at-solving-and-judging-but-can-t.jsonld"}}