Elias in the Lighthouse, Again? Diagnosing Low Diversity in LLM Stories

About a month ago I wrote a blog post that spoke to the rise of poor quality content as a result of agentic workflows, but it primarily focused on ethics: ending with presenting how a synthetic author named "Elias Thorne" is now rising in _alternative Cancer treatment_ book categories on Amazon, and questioning how this will affect the web over time. That post is here if you're interested: https://danielmay.co.uk/posts/cheap-agents-alumni-shirts-and...

A few weeks after, a doctoral research team from Cornell published this paper to arXiv that digs into more of the same phenomenon scientifically (n=20k vs my 8!) and examines the training data to try to understand cause. I'm interested to continue to see what the second-order effects of this phenomena will be.