The system prompt for OpenAI\u2019s Codex CLI contains a perplexing and repeated warning for the most recent GPT model to \u201cnever talk about goblins, gremlins, raccoons, trolls, ogres, pigeons, or other animals or creatures unless it is absolutely and unambiguously relevant to the user\u2019s query.\u201d<\/p>\n
The explicit operational warning was made public last week<\/a> as part of the latest open source code for Codex CLI that OpenAI posted on GitHub<\/a>. The prohibition is repeated twice in a 3,500-plus word set of \u201cbase instructions\u201d for the recently released GPT-5.5, alongside more anodyne reminders not to \u201cuse emojis or em dashes unless explicitly instructed\u201d and to \u201cnever use destructive commands like \u2018git reset –hard\u2019 or \u2018git checkout –\u2019 unless the user has clearly asked for that operation.\u201d<\/p>\n 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<\/a> evidence<\/a> on social media<\/a> shows some users complaining<\/a> about GPT\u2019s penchant for focusing on goblins in completely unrelated conversations in recent days.<\/p>\n OpenAI employee Nick Pash, who works on Codex, insists on social media<\/a> that this \u201cisn\u2019t a marketing gimmick\u201d to get people talking about GPT-5.5 and Codex. But that hasn\u2019t stopped some OpenAI executives from leaning into the joke as word of the system prompt spread. \u201cFeels like codex is having a ChatGPT moment. I meant a goblin moment, sorry,\u201d OpenAI CEO Sam Altman wrote on social media Wednesday morning<\/a>.<\/p>\n","protected":false},"excerpt":{"rendered":"The system prompt for OpenAI\u2019s Codex CLI contains a perplexing and repeated warning for the most recent GPT…\n","protected":false},"author":2,"featured_media":639661,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[256,254,255,64,63,105],"class_list":["post-639660","post","type-post","status-publish","format-standard","has-post-thumbnail","category-artificial-intelligence","tag-ai","tag-artificial-intelligence","tag-artificialintelligence","tag-au","tag-australia","tag-technology"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/posts\/639660","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/comments?post=639660"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/posts\/639660\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/media\/639661"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/media?parent=639660"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/categories?post=639660"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/tags?post=639660"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}