OpenAI 更新 Model Spec，围绕五项核心价值重构模型行为准则
OpenAI sets new behavioral guidelines for AI models that have already proven hard to control
OpenAI 更新了 Model Spec，要求 GPT 模型读懂对话历史里的真实意图，还会主动交代自己的假设，规则里首次引入了可纠正性。
OpenAI 更新了 Model Spec 行为准则，将规则重构为五项核心价值，包括忠实于人类意图和可纠正性。新版要求 GPT 模型结合对话历史判断用户真实意图，并主动披露自身的假设。OpenAI 也承认模型能否真正遵守这些规则仍是挑战。
OpenAI sets new behavioral guidelines for AI models that have already proven hard to control
OpenAI has updated its Model Spec, restructuring its AI behavior guidelines around five core values, including faithfulness to human intent and correctability. GPT models should now draw on conversation history to figure out what users actually want and disclose their own assumptions. Whether the models follow these rules is another matter. The article OpenAI sets new behavioral guidelines for AI models that have already proven hard to control appeared first on The Decoder .
