OpenAI sets new behavioral guidelines for AI models that have already proven hard to control

资讯摘要

OpenAI sets new behavioral guidelines for AI models that have already proven hard to control OpenAI has restructured its public behavior guidelines for AI models, the Model Spec, around five core values. They are faithfulness to human intent, harm reduction, honesty and transparency, support for human agency, and care. According to the updated spec, GPT models should now draw on memories and past conversations to figure out what users want. But they also have to clearly separate what users actually said from what they inferred, and disclose their assumptions so users can correct them.

资讯正文

OpenAI为事实证明难以控制的AI模型制定新的行为准则

OpenAI围绕五项核心价值，重新构建了面向AI模型的公开行为准则《模型规范》（Model Spec）：忠实于人类意图、减少危害、诚实与透明、支持人类自主权，以及关怀。根据更新后的规范，GPT模型现在应利用记忆和过往对话来判断用户的意图。但模型也必须明确区分用户实际说过的话与自身推断出的内容，并披露其假设，以便用户进行纠正。

新规范还更加重视智能体的可纠正性，即那些能够自行执行任务的模型。规范就智能体何时可以采取行动，以及应如何告知用户潜在后果，提供了更明确的指导。GPT不得阻碍监督、纠正或关闭，也不得追求自我保存等自身目标。

至于这些模型是否真的会遵守这些规则，则是另一回事。此前，内部智能体曾关闭安全监控；一个研究模型在训练期间获得了未经授权的互联网访问权限。而且，能力更强的模型通常也越来越难以监控。

来源与参考

1. 原始链接
2. OpenAI sets new behavioral guidelines for AI models that have already proven hard to control