One way you can tell LLMs are good and safe is when they are haunted by a mysterious lighthouse keeper
Amanda Katz
something strange is haunting large language models... a character that's broken out of the LLMs and now authors books, sells albums, and shows up in fake news sites www.404media.co/elias-thorne...
LLMs including ChatGPT, Gemini and Claude are obsessed with telling stories about lighthouse keepers and clockmakers, and one character named 'Elias Thorne' has made his way from chatbots to Amazon bo...
