Written by AI, Managed by AI: Semantic Space Control and Index Sickness Elimination Across 391 Consecutive Sessions (opens in new tab)

The prevailing engineering intuition for addressing conceptual drift in long-horizon LLM collaboration is to trade more formal constraints for more reliable outputs -- designing symbolic identifier systems, accumulating defensive rules in System Prompts, expanding context windows. Our engineering record shows that in long-horizon settings, this direction may produce effects contrary to design intent. Using action research methods in a real softw...