Glossary · RSI and self-improvement
Evaluator co-evolution
Tests, rubrics, or judges that evolve together with the policy they supervise. Co-evolution may escape a self-confirming loop or add a second story to it, so it needs a fixed anchor channel outside the loop.
Defined in
Handbook · Agents and self-improvementSelf-improvement and evaluator co-evolutionWhen a system can change what defines "better", the evaluator becomes the load-bearing wall. What changes, who validates, how loops fail.Related terms
- Self-confirming loop
- Generator and evaluator share correlated blind spots, so selection or training amplifies common errors. It needs no adversary, only correlated bias.
- O/A/P channels
- Three separated measurement channels: an optimized channel (O), cheap, dense, and allowed to co-evolve; an anchor channel (A) that certifies independently and stays out of training objectives; and a production channel (P) of real outcomes and incidents.
Where it comes up
- Channels, independence, and anchor burnHandbook · Lifecycle