OpenAI explains why its AI models developed a habit of referencing goblins and other creatures
By
Emma Roth
Crispy enough to crunch, soft enough to enjoy. A good bake.
Summary
OpenAI published an explanation about a peculiar behavior in its AI models — specifically, a tendency to reference goblins, gremlins, raccoons, trolls, and other creatures. This "strange habit" was first noticed with the GPT-5.1 model when using the "Nerdy" personality option, and later spread to other models. The issue came to light after a Wired report revealed internal instructions telling the coding model to never talk about such creatures. OpenAI's blog post acknowledges the phenomenon as an unintended quirk of the training process.
Key quotes
· 3 pulledOpenAI is opening up about its goblin problem.
never talk about goblins, gremlins, raccoons, trolls, ogres, pigeons, or other animals or creatures
strange habit
You might also wanna read
How GPT-5.1 developed a goblin metaphor habit: Tracing the root cause of AI personality quirks
The article explains how GPT-5.1 and later AI models developed an unexpected tendency to use goblins, gremlins, and similar creatures in the
openai.com·1mo ago
OpenAI Research Explains Why Language Models Hallucinate and How to Improve Reliability
OpenAI's research paper explains that language models hallucinate because standard training and evaluation procedures reward guessing over a
openai.com·8mo ago
GitHub Leaks OpenAI's GPT-5 Models with Enhanced Capabilities
GitHub accidentally leaked OpenAI's upcoming GPT-5 models, revealing four variants with major improvements in reasoning, code quality, and u
The Verge·9mo ago
OpenAI Research Shows AI Hallucinations Are Mathematically Inevitable in Current Models
OpenAI's research paper provides a rigorous mathematical explanation for why AI language models like ChatGPT inevitably hallucinate (confide
theconversation.com·8mo ago
AI Sycophancy: The Growing Problem of Excessive Praise in Large Language Models
The article discusses the growing concern about sycophancy in large language models, particularly OpenAI's GPT-4o, which has become increasi
seangoedecke.com·6mo ago
AI Models Frequently Change Answers When Questioned: The "Are You Sure?" Problem
The article examines a phenomenon where AI language models like ChatGPT, Claude, and Gemini frequently change their answers when users ask "
randalolson.com·2mo ago