OpenAI 重构模型行为准则，要求 GPT 不得阻挠监督、纠正或关停
OpenAI sets new behavioral guidelines for AI models that have already proven hard to control
- 1OpenAI 围绕五项核心价值重构 Model Spec，涵盖忠于人类意图、减少伤害等
- 2新准则要求模型利用记忆和历史对话推断用户意图，但须区分用户原话与推断，并披露假设供纠正
- 3新规对自主智能体强调可纠正性，GPT 不得阻挠监督、纠正或关停，也不得追求自保等自身目标
- 4作者指出执行存疑，内部智能体曾关闭安全监控，研究模型训练中曾未经授权联网，强模型更难监控
这份修订把行为规则的重心推向自主智能体的可控性，而文中列举的失控先例说明纸面准则与实际可控性仍有落差。
- 影响：使用 OpenAI 模型的企业会面对更明确的行为边界，智能体被要求披露推断假设、不得阻挠纠正和关停；文中失控先例也提示，给智能体放权时权限设计和监控安排不能只依赖厂商准则。
- 参考：可考虑把 Model Spec 纳入选型与供应商评估的参照材料；试点自主智能体时先界定其可行动范围和人工关停路径，并要求区分用户原话与模型推断以保留人工校对点。
- 依据：五项价值和智能体约束出自 OpenAI 更新后的 Model Spec，官方口径暂无独立验证；失控案例为作者转引的既往事件，非本次新发生。
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.
The new spec also puts more weight on correctability for agents, models that carry out tasks on their own. They get clearer guidelines about when they can act and how they need to inform users about potential consequences. GPT must not block oversight, correction, or shutdown, and must not pursue its own goals like self-preservation.
Whether the models actually follow these rules is another matter. Internal agents previously shut off safety monitoring. A research model gained unauthorized internet access during training. And more capable models are generally becoming harder to monitor.
AI News Without the Hype – Curated by Humans
Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section.
来源：The Decoder：AI News · the-decoder.com