深度循环模型更难监控
AI 导读
通过深度循环让模型变得更深，确实会让它们更难被监控 但当他看到 OAI 已经部署了这类推理方式的模型好几个月后，他的整套讨论就显得非常古板/学术了
正文
Making models deeper through recurrence in depth does make them harder to monitor
but his whole discussion seems very quaint/academic when OAI has deployed models for many months that reason like this