OpenAI’s Codex CLI system prompt includes a puzzling, duplicated directive for the newest 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.”
That explicit operational warning was made public last week as part of the latest open-source Codex CLI code OpenAI posted on GitHub. The restriction appears twice inside a more than 3,500-word set of “base instructions” for the recently released GPT-5.5, alongside milder cautions 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.”
System prompt entries for earlier models contained in the same JSON file do not include the specific ban on mentioning goblins and similar creatures, suggesting OpenAI is dealing with a new issue that emerged with the latest release. Anecdotal evidence on social media shows some users complaining about GPT’s tendency to bring up goblins in otherwise unrelated conversations in recent days.
OpenAI engineer Nick Pash, who works on Codex, insists on social media that this “isn’t a marketing gimmick” intended to get people talking about GPT-5.5 and Codex. Still, that hasn’t stopped a few OpenAI executives from leaning into the joke as 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.
