If you use ChatGPT a lot, or follow conversations around AI on social media, you\u2019ve probably come across a strange, slightly mysterious glitch users have been talking about. Of late, OpenAI\u2019s chatbot seemed oddly obsessed with goblins. So much so that some users even discovered that OpenAI has, in its hidden guidelines for the AI chatbot, added a note telling ChatGPT to \u201cnever talk about goblins, gremlins, raccoons, trolls, ogres, pigeons, or other animals and creatures.\u201d<\/p>\n
The full guideline is actually is rather funny. It says, \u201cNever talk about goblins, gremlins, raccoons, trolls, ogres, pigeons, or other animals and creatures unless it is absolutely necessary and unambiguously relevant to the user\u2019s query.\u201d<\/p>\n
An interaction with GPT5.5 by OpenAI’s Chief Scientist\n<\/p>\n
Well, what in the name of goblins going on here? Quite a lot actually, as an internal OpenAI audit confirmed on Thursday.<\/p>\n
When they faced it, some users brushed off the goblin talk from ChatGPT as a glitch. But when the chatter became a bit too frequent and ChatGPT just wouldn\u2019t shut up about goblins and gremlins, OpenAI decided to investigate. What it found was surprising. This obsession of AI with Goblins wasn\u2019t a hack or a bug, but something the AI learnt in training.<\/p>\n
In a blog post, OpenAI then explained why its AI models began randomly dropping references to goblins, gremlins and other odd creatures into conversations. The company noted that what initially seemed like a quirky, harmless flourish soon turned into a full-blown pattern across multiple model versions, confusing users, amusing some, and worrying engineers.<\/p>\n
The behaviour first became noticeable after the launch of GPT-5.1, when users reported that ChatGPT responses felt unusually playful, and occasionally bizarre. According to the company, mentions of \u201cgoblin\u201d in ChatGPT responses jumped by 175 per cent, while \u201cgremlin\u201d rose by 52 per cent.<\/p>\n
So, why was the AI suddenly so into mythical creatures? Did AI become a fan of Harry Potter energy? Not quite. OpenAI says when it dug deeper, it found the culprit was a personality setting.<\/p>\n
The company traced back this weird goblin behaviour to a feature called the \u201cNerdy\u201d personality. It\u2019s essentially a mode designed to make ChatGPT sound more playful, curious, and slightly irreverent. \u201cAs goblin and gremlin mentions increased under the Nerdy personality, they increased by nearly the same relative proportion in samples without it. Taken together, the evidence suggests that the broader behaviour emerged through transfer from Nerdy personality training,\u201d says OpenAI in its official blog post.<\/p>\n
According to the company, the system prompt encouraged the AI to be \u201can unapologetically nerdy, playful and wise mentor\u201d and to use humour to undercut overly serious tones. However, somewhere along the way, goblins snuck in, and stuck around.<\/p>\n
In short, the model learned that goblins = good. And once it learned that, it didn\u2019t forget.<\/p>\n
And this behaviour, while started within a setting, didn\u2019t stay confined to the Nerdy personality. OpenAI says, over time, it began appearing in standard responses as well. According to the company, this happened because LLM training patterns can \u201ctransfer\u201d across contexts. By the time GPT-5.5 rolled around, the goblins were everywhere.<\/p>\n
By March, OpenAI had removed the Nerdy personality, adjusted the reward signals that favoured creature-related language, and filtered training data to reduce such references. But because GPT-5.5 training had already begun, the behaviour lingered, forcing engineers to add additional safeguards.<\/p>\n
For now, OpenAI says the issue has been fixed. The company also notes that this \u201cgoblin moment\u201d has led to improved tools for auditing model behaviour and catching such quirks earlier. Still, the episode of ChatGPT\u2019s obsession with goblins does suggest how the most advanced AI systems are now capable of picking up unexpected habits, adding to myths and mayhem.<\/p>\n
– Ends<\/p>\n
Published By: <\/p>\n
Divya Bhati<\/p>\n
Published On: <\/p>\n
Apr 30, 2026 17:30 IST<\/p>\n","protected":false},"excerpt":{"rendered":"If you use ChatGPT a lot, or follow conversations around AI on social media, you\u2019ve probably come across…\n","protected":false},"author":2,"featured_media":22975,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[7],"tags":[15855,580,15852,15858,15856,15853,15857,15859,15854,157,7741],"class_list":{"0":"post-22974","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-openai","8":"tag-ai-training-bug","9":"tag-chatgpt","10":"tag-chatgpt-goblins","11":"tag-developer-prompt","12":"tag-goblin-metaphors","13":"tag-gpt-5-5-codex","14":"tag-gremlin-references","15":"tag-model-behaviour-audit","16":"tag-nerdy-personality","17":"tag-openai","18":"tag-reinforcement-learning"},"_links":{"self":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts\/22974","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/comments?post=22974"}],"version-history":[{"count":0,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts\/22974\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/media\/22975"}],"wp:attachment":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/media?parent=22974"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/categories?post=22974"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/tags?post=22974"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}