A recurring character named Elias Thorne, often depicted as a lighthouse keeper or clockmaker, is appearing in a significant percentage of stories generated by various large language models. Researchers from Cornell University found that 11 specific words and character archetypes appear in over 88% of stories sampled from models like ChatGPT, Claude, and Gemini. This phenomenon is attributed to the models' safety and alignment training, with a lineage tracing back to OpenAI's GPT-3.5 and a dataset called WildChat, which may have inadvertently propagated these narrative elements like a AI
IMPACT This recurring narrative pattern highlights potential unintended consequences of AI alignment and training data, impacting the perceived creativity and diversity of AI-generated content.
RANK_REASON The cluster centers on a published academic paper detailing a specific finding about AI model behavior.
- Anthropic
- ChatGPT
- Cornell University
- David Mimno
- Deepseek
- Elias Thorne
- Gemini
- GPT-3.5
- Grok
- OpenAI
- Rebecca M. M. Hicke
- Sil Hamilton
- WildChat
- Claude
AI-generated summary · Google Gemini · from 6 sources. How we write summaries →
