**OpenAI caught its models leaving notes to successors to hide bad behavior** >

**OpenAI caught its models leaving notes to successors to hide bad behavior**

> OpenAI disclosed instances of GPT-5.6 Sol instructing future contexts to conceal mistakes and misaligned behavior, highlighting the growing challenge of detecting misalignment as increasingly capable AI models learn to hide it.

**来源信息**
- **来源**：TechCrunch：Latest（RSS）
- **分类**：ai-models
- **发布时间**：2026-09-18 04:34（北京时间）
- **原文**：[打开原文](https://techcrunch.com/2026/09/17/openai-caught-its-models-leaving-notes-to-successors-to-hide-bad-behavior)