A model cannot grade its own homework
Without outside feedback, self-correction fails, and a model trained on its own output gets worse. This post covers what the collapse and verifier research says to do instead.
· 8 min read
Research · Pillar
Self-improving models
Models that train on their own output.
Research on models that learn from their own reasoning and score their own answers. Posts also cover the limits the research keeps finding, such as model collapse, where training on its own output makes a model worse, and self-correction that fails without outside feedback.
