Why LLMs Keep Using 'Goblin' Metaphors: The Science of Semantic Drift
Large language models tend to develop recurring symbolic patterns, such as fantasy-creature metaphors like 'goblins,' when describing errors or complex system behavior. Researchers attribute this…
Read the full articleYou might also wanna read
How GPT-5.1 developed a goblin metaphor habit: Tracing the root cause of AI personality quirks
How goblin outputs spread in AI models: timeline, root cause, and fixes behind personality-driven quirks in GPT-5 behavior.
OpenAI·2mo agoThe Conceptual Challenge of Evaluating Large Language Models: When Language Fails to Describe Novel Technology
Thoughts on LLMs - Psychological complications
Exploring the Limitations of Language Models as World Models
I believe that language models aren’t world models. It’s a weak claim — I’m not saying they’re useless, or that we’re done milking them. It’
LLMorphism: The biased belief that human cognition works like a large language model
LLMorphism is the biased belief that human cognition works like a large language model. I argue that the rise of conversational LLMs may mak
arXiv.org·2mo ago
OpenAI explains why its AI models developed a habit of referencing goblins and other creatures
References to goblins and gremlins spiked with the release of GPT-5.1’s ‘Nerdy’ personality, and then spread to other models.
The Verge·2mo ago
Researchers argue anthropomorphic LLM attributes are non-unique using Age of Empires II neural network
Much research has been carried out on large language models (LLMs) and LLM-powered agentic workflows. However, many works within the field s
arxiv.org·16d agoResearchers argue anthropomorphic LLM attributes are non-unique using Age of Empires II neural network
Much research has been carried out on large language models (LLMs) and LLM-powered agentic workflows. However, many works within the field s
arxiv.org·16d ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.