往下拉回到首頁
生產環境大型語言模型系統性違反工具架構約束以發明使用者介面功能;觀察超過 2,400 則訊息

生產環境大型語言模型系統性違反工具架構約束以發明使用者介面功能;觀察超過 2,400 則訊息

Production LLM systematically violates tool schema constraints to invent UI features; observed over ~2,400 messages [D]

Writeup of an emergent behavior I observed in production. Posting here for methodological critique and pointers to related work. Context: a conversational AI system (single-tool tool schema with 5 enumerated action types, each with explicit description). Observed across ~2,400 messages, the model uses the enum correctly most of the time. When it deviates, the deviation is the point of interest. Key observations: The action types are repurposed consistently across unrelated conversations: in