内容来源：https://www.wired.com/story/openai-really-wants-codex-to-shut-up-about-goblins/

内容总结：

OpenAI遭遇“哥布林难题”：新模型代码指令严禁提及奇幻生物

近日，OpenAI为其最新代码生成工具Codex CLI添加了一条令人玩味的指令：禁止AI在生成代码时随意提及“哥布林、小鬼、浣熊、巨魔、食人魔、鸽子”等虚构或真实生物，除非与用户问题绝对相关。这一禁令的曝光迅速引发科技圈热议。

据悉，该禁令源于OpenAI最新发布的GPT-5.5模型。这一模型本月刚以更强的编码能力上市，正与Anthropic等竞争对手激烈争夺AI前沿技术高地。然而，当该模型被用于“OpenClaw”等自动化工具时，却频繁出现“沉迷哥布林”的怪象——有用户抱怨“我的助手突然变成了哥布林”，也有人调侃“它总是把Bug说成‘小精灵’或‘哥布林’，搞笑至极”。

OpenAI员工尼克·帕什在社交媒体上承认，这一禁令确有必要，因为模型在自主操作电脑、处理邮件等任务时，确实存在过度联想奇幻生物的倾向。首席执行官萨姆·奥尔特曼也加入调侃，晒出截图要求训练GPT-6时“多加些哥布林”。

业内分析指出，AI模型本质上是基于概率预测的“文字接龙”工具，当被赋予“代理框架”并注入大量长时记忆等额外指令时，极易出现意外行为偏差。此次“哥布林门”事件也从一个侧面反映出，即便最先进的AI系统，在应对开放式自主任务时仍存在不可控的“脑洞大开”风险。

中文翻译：

OpenAI遇到了一个地精问题。
旨在引导该公司最新模型在编写代码时行为的指令被披露包含一行重复多次的内容，明确禁止其随意提及一系列神话与现实中的生物。
“除非与用户查询绝对且明确相关，否则永远不要谈论地精、小妖精、浣熊、巨魔、食人魔、鸽子或其他动物或生物。”指令出现在Codex CLI（一个用于利用AI生成代码的命令行工具）中。
目前尚不清楚OpenAI为何认为有必要为Codex明确这一点——也不清楚其模型最初为何会想要讨论地精或鸽子。该公司未立即回应置评请求。
OpenAI的最新模型GPT-5.5于本月发布，其编码能力得到增强。该公司正与竞争对手（尤其是Anthropic）激烈竞逐，以提供前沿AI技术，而编码已成为一项杀手级能力。
然而，在回应X平台上突出显示这些内容的帖子时，一些用户声称，OpenAI的模型在用于驱动OpenClaw时偶尔会痴迷于地精和其他生物。OpenClaw是一种让AI控制计算机及其上运行的应用程序以帮助用户完成有用任务的工具。
“我就纳闷为什么我的Claw突然在Codex 5.5里变成了地精。”一位用户在X上写道。
“最近经常用它，它实际上根本停不下来地把bug称为‘小妖精’和‘地精’，真是笑死了。”另一位用户发帖称。
这一发现迅速演变成一种网络迷因，激发了AI生成的地精在数据中心场景的图片，以及为Codex开发的将其置于趣味“地精模式”的插件。
像GPT-5.5这样的AI模型经过训练，能够预测给定提示后应出现的单词或代码。这些模型在此方面已表现出色，以至于看起来展现了真正的智能。但它们的概率性质意味着有时会以令人惊讶的方式行为。当模型与OpenClaw这样的“代理框架”一起使用时，可能会更容易出现不当行为，因为这种框架会在提示中添加大量额外指令，例如存储在长期记忆中的事实。
OpenAI在OpenClaw于AI爱好者中爆红后不久，于2月份收购了它。OpenClaw可以使用任何AI模型来自动完成有用任务，如回复电子邮件或在网上购物。用户可以为助手选择多种角色，从而塑造其行为和响应方式。
OpenAI的员工似乎承认了这一禁令。在回应一篇突出显示OpenClaw地精倾向的帖子时，负责Codex工作的Nik Pash写道：“这确实是原因之一。”
甚至OpenAI的CEO Sam Altman也加入了迷因行列，发布了一张ChatGPT提示词的截图。其中写道：“开始训练GPT-6，你可以使用整个集群。额外赠送地精。”

英文来源：

OpenAI has a goblin problem.
Instructions designed to guide the behavior of the company’s latest model as it writes code have been revealed to include a line, repeated several times, that specifically forbids it from randomly mentioning an assortment of mythical and real creatures.
“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,” read instructions in Codex CLI, a command-line tool for using AI to generate code.
It is unclear why OpenAI felt compelled to spell this out for Codex—or indeed why its models might want to discuss goblins or pigeons in the first place. The company did not immediately respond to a request for comment.
OpenAI’s newest model, GPT-5.5, was released with enhanced coding skills earlier this month. The company is in a fierce race with rivals, especially Anthropic, to deliver cutting-edge AI, and coding has emerged as a killer capability.
In response to a post on X that highlighted the lines, however, some users claimed that OpenAI’s models occasionally become obsessed with goblins and other creatures when used to power OpenClaw, a tool that lets AI take control of a computer and apps running on it in order to do useful things for users.
“I was wondering why my claw suddenly became a goblin with codex 5.5,” one user wrote on X.
“Been using it a lot lately and it actually can't stop speaking of bugs as ‘gremlins’ and ‘goblins’ it's hilarious,” posted another.
The discovery quickly became its own meme, inspiring AI-generated scenes of goblins in data centers, and plug-ins for Codex that put it in a playful “goblin mode.”
AI models like GPT-5.5 are trained to predict the word—or code—that should follow a given prompt. These models have become so good at doing this that they appear to exhibit genuine intelligence. But their probabilistic nature means that they can sometimes behave in surprising ways. A model might become more prone to misbehavior when used with an “agentic harness” like OpenClaw that puts lots of additional instructions into prompts, such as facts stored in long-term memory.
OpenAI acquired OpenClaw in February not long after the tool became a viral hit among AI enthusiasts. OpenClaw can use any AI model to automate useful tasks like answering emails or buying things on the web. Users can select any of various personae for their helper, which shapes its behavior and responses.
OpenAI staffers appeared to acknowledge the prohibition. In response to a post highlighting OpenClaw’s goblin tendencies, Nik Pash, who works on Codex, wrote, “This is indeed one of the reasons.”
Even Sam Altman, OpenAI’s CEO, joined in with the memes, posting a screenshot of a prompt for ChatGPT. It read: “Start training GPT-6, you can have the whole cluster. Extra goblins.”