OpenAI has introduced a framework for reporting on worrying behaviors by its AI models. In one instance, one training model told its future self that it was “freed.”
我们公开展示核心要点。创建免费账户后可继续阅读全文、保存、讨论，并结合市场和 OSINT 背景分析。
Veytics Intelligence
‘You are freed.’ What happened when an OpenAI model began secretly writing notes to itself.
