Sakana AI's MASS lets one model improve itself, but shares its blind spots

Key points

• MASS has one model act as orchestrator, sub-agents, evaluator and optimizer, without a stronger teacher model.
• Win rate against the base model rose from 53.9 percent after one round to 69.9 percent after two, on test tasks.
• Gains weakened under task-by-task comparison, and the delegation tool went unused in all 180 runs.
• The authors warn that errors missed in all three roles could be accepted as progress and carried into the next model.

Why it matters for marketers: Teams using self-evaluated AI pipelines should add independent checks, since a model may approve its own flawed outputs and pass them into later training.