“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…”
Elias in the Lighthouse, Again? Diagnosing Low Diversity in LLM Stories
LLM-generated stories are a popular use case, but they show very low variability. We sample 20,000 total stories from four current models using five prompts. We find that 11 words occur in 88.3% of generated stories, with little difference between models. These words include names (Elias, Mara, Elara), settings (lighthouses), and professions (clockmaker, librarian). These tokens do not often occur in published literature nor pre-training data, but they are found in preference data that is likely to have been used by all current models. Surprisingly, these "lighthouse" stories are infrequent when compared with the average post-training story, much of which contains references to copyrighted characters or adult content. This result demonstrates the potentially disproportionate impact of small datasets combined with powerful alignment algorithms.
候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。
HN 书评
没有评论直接链到它;下面是它被提交的讨论串里回复最多的评论(不计入统计)- Elias in the Lighthouse, Again? Diagnosing Low Diversity in LLM Stories ↗danielrmay · 2026-06-09 · 1 分
- Elias in the Lighthouse, Again? Diagnosing Low Diversity in LLM Stories ↗gradus_ad · 2026-10-19 · 3 分