Static

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

First reported by The Decoder · 1m ago

The signal ●○○○ Brief pending · reported by The Decoder, the single source so far

What happened

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 roun...

Source description shown. AI brief pending.

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

Related