OpenAI really wants the Codex to shut up about the orcs

OpenAI has a goblin problem.

The instructions are designed to guide the behavior of the company’s latest model while writing code revealed to include A line repeated several times specifically prevents him from randomly mentioning a variety of mythical and real creatures.

“Never talk about orcs, goblins, raccoons, trolls, ogres, pigeons, or other animals or creatures unless absolutely and unambiguously relevant to the user’s query,” read instructions in the Codex CLI, a command-line tool for using artificial intelligence to generate code.

It is not clear why OpenAI She felt compelled to clarify this matter Codex Alimentarius– or indeed why her models would want to discuss goblins or pigeons in the first place. The company did not immediately respond to a request for comment.

OpenAI’s latest model, GPT-5.5, was released with improved programming skills earlier this month. The company is In a fierce race with competitorsespecially AnthropicTo introduce the latest artificial intelligence technologies, programming has emerged as a killer ability.

In response to A Share on X That highlighted the lines, however, some users claimed that OpenAI models sometimes become obsessed with goblins and other creatures when they use energy OpenClawa tool that allows artificial intelligence to control a computer and the applications 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 said books On X.

“I’ve been using it a lot lately, and I actually can’t stop talking about bugs as ‘gremlins’ and ‘goblins’. It’s funny.” to publish last.

This discovery quickly became its own and inspiring meme Scenes generated by artificial intelligence Of sprites in data centers, and Codex plug-ins Which puts her in a fun “goblin mode.”

AI models like GPT-5.5 are trained to predict which word – or code – should follow a given prompt. These models have become so good at doing this that they display real intelligence. But their probabilistic nature means they can sometimes behave in surprising ways. The form may become more vulnerable to misbehavior when used with a “utility” like OpenClaw that puts a lot of extra instructions into the claims, such as facts stored in long-term memory.

OpenAI acquired OpenClaw in February shortly after the tool became popular among AI enthusiasts. OpenClaw can use any AI model to automate useful tasks like answering emails or buying things on the web. Users can choose any of the different personalities of their assistant, shaping his behavior and responses.

OpenAI employees appear to acknowledge the ban. In response to a post highlighting OpenClaw’s daemon tendencies, Nick Bash, who works at Codex, said, books“That’s actually one of the reasons.”

Even Sam Altman, CEO of OpenAI, has joined in on the memes, send Screenshot of ChatGPT prompt. It read: “Start training GPT-6, you can get the whole set. More sprites.”