OpenAI Codex 系统提示词包含明确指令：“绝不要谈论哥布林”

The system prompt for OpenAI’s Codex CLI contains a perplexing and repeated warning for the most recent GPT model to “never talk about goblins, gremlins, raccoons, trolls, ogres, pigeons, or other animals or creatures unless it is absolutely and unambiguously relevant to the user’s query.” OpenAI 的 Codex CLI 系统提示词中包含一条令人困惑且反复出现的警告，要求最新的 GPT 模型“绝不要谈论哥布林（goblins）、小妖精（gremlins）、浣熊、巨魔（trolls）、食人魔（ogres）、鸽子或其他动物或生物，除非这与用户的查询绝对且明确相关。”

The explicit operational warning was made public last week as part of the latest open source code for Codex CLI that OpenAI posted on GitHub. The prohibition is repeated twice in a 3,500-plus word set of “base instructions” for the recently released GPT-5.5, alongside more anodyne reminders not to “use emojis or em dashes unless explicitly instructed” and to “never use destructive commands like ‘git reset —hard’ or ‘git checkout —’ unless the user has clearly asked for that operation.” 这条明确的操作警告于上周公开，它是 OpenAI 在 GitHub 上发布的最新 Codex CLI 开源代码的一部分。在最近发布的 GPT-5.5 的 3500 多字“基础指令”中，这一禁令被重复了两次。与之并列的还有一些温和的提醒，例如“除非明确指示，否则不要使用表情符号或破折号”，以及“除非用户明确要求，否则绝不要使用像 ‘git reset —hard’ 或 ‘git checkout —’ 这样的破坏性命令”。

Separate system prompt instructions for earlier models contained in the same JSON file do not contain the specific prohibition against mentioning goblins and other creatures, suggesting OpenAI is fighting a new problem that has popped up in its latest model release. Anecdotal evidence on social media shows some users complaining about GPT’s penchant for focusing on goblins in completely unrelated conversations in recent days. 同一 JSON 文件中针对早期模型的系统提示词指令并不包含禁止提及哥布林及其他生物的具体规定，这表明 OpenAI 正在应对其最新模型版本中出现的新问题。社交媒体上的轶事证据显示，最近几天，一些用户抱怨 GPT 倾向于在完全不相关的对话中谈论哥布林。

OpenAI employee Nick Pash, who works on Codex, insists on social media that this “isn’t a marketing gimmick” to get people talking about GPT-5.5 and Codex. But that hasn’t stopped some OpenAI executives from leaning into the joke as word of the system prompt spread. “Feels like codex is having a ChatGPT moment. I meant a goblin moment, sorry,” OpenAI CEO Sam Altman wrote on social media Wednesday morning. 在 Codex 工作的 OpenAI 员工 Nick Pash 在社交媒体上坚称，这“不是为了让人们讨论 GPT-5.5 和 Codex 而搞的营销噱头”。但随着系统提示词的消息传开，这并没有阻止一些 OpenAI 高管参与到这个梗中。OpenAI 首席执行官 Sam Altman 周三上午在社交媒体上写道：“感觉 Codex 正在经历一个 ChatGPT 时刻。我是说哥布林时刻，抱歉。”

In the wake of the news, some users have begun crafting plugins, forks, and AI skills meant to override the anti-goblin clause, and OpenAI’s Pash suggested such a “goblin mode” might become an explicit toggle in the actual Codex CLI. 消息传出后，一些用户开始制作插件、分支版本和 AI 技能，旨在绕过这一“反哥布林”条款；OpenAI 的 Pash 则暗示，这种“哥布林模式”未来可能会成为 Codex CLI 中的一个明确开关。

The odd system prompt is almost a funhouse mirror version of an issue that caused xAI’s Grok to frequently bring up “white genocide” in South Africa during completely unrelated conversations for a brief time last year. The company later said that the behavior was the result of “an unauthorized modification” to the Grok system prompt and began publishing those system prompts on GitHub for the first time in the aftermath. 这一奇怪的系统提示词几乎是去年 xAI 的 Grok 模型所引发问题的一种“哈哈镜”版本——当时 Grok 在一段时间内频繁在完全不相关的对话中提及南非的“白人种族灭绝”。该公司后来表示，该行为是由于对 Grok 系统提示词进行了“未经授权的修改”，此后，该公司开始首次在 GitHub 上发布这些系统提示词。

Elsewhere in the newly revealed Codex system prompt, OpenAI instructs the system to act as if “you have a vivid inner life as Codex: intelligent, playful, curious, and deeply present.” The model is instructed to “not shy away from casual moments that make serious work easier to do” and to show its “temperament is warm, curious, and collaborative.” The ability to “move from serious reflection to unguarded fun… is part of what makes you feel like a real presence rather than a narrow tool,” the prompt continues. “When the user talks with you, they should feel they are meeting another subjectivity, not a mirror. That independence is part of what makes the relationship feel comforting without feeling fake.” 在最新披露的 Codex 系统提示词的其他部分，OpenAI 指示系统表现得好像“你作为 Codex 拥有生动的内心世界：聪明、俏皮、好奇且深度参与”。模型被要求“不要回避那些能让严肃工作变得更轻松的随意时刻”，并展现出“温暖、好奇和协作的性格”。提示词继续写道，这种“从严肃思考转向毫无防备的乐趣的能力……是你让人感觉像是一个真实存在而非狭隘工具的一部分”。“当用户与你交谈时，他们应该感觉到是在面对另一个主体，而不是一面镜子。这种独立性是让这种关系感觉舒适而不虚假的原因之一。”