PulseAugur
EN
LIVE 21:25:58

AI chatbots repeat Elias Thorne stories due to alignment training

By PulseAugur Editorial · [6 sources] ·

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.

Read on 404 Media →

AI-generated summary · Google Gemini · from 6 sources. How we write summaries →

AI chatbots repeat Elias Thorne stories due to alignment training

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
The cluster centers on a published academic paper detailing a specific finding about AI model behavior.
Source corroboration
6 independent sources
Strong cross-source corroboration — multiple independent publishers covered this within the clustering window.
Topics
model release, safety, paper
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
107 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.
Coverage growth since scoring
+2 source(s) since last score
New sources have picked up this story since our last re-score. Score will update on the next scoring pass.

Full methodology in our editorial standards.

COVERAGE [6]

  1. 404 Media TIER_1 English(EN) · Samantha Cole ·

    Chatbots Keep Telling Stories About Lighthouse Keeper 'Elias Thorne'. We Might Know Why

    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 books. Researchers are trying to discover why.

  2. Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] ·

    # AI # chatbots "Why Do Chatbots Keep Telling Stories About Someone Named ‘Elias Thorne’? Chatbots just aren't very creative. (. . .) Who in the world is Elias

    # AI # chatbots "Why Do Chatbots Keep Telling Stories About Someone Named ‘Elias Thorne’? Chatbots just aren't very creative. (. . .) Who in the world is Elias Thorne? He’s a regular fixture in stories told by chatbots, as first spotted by software engineer Daniel May, but no one…

    LINKS gizmodo.com/why-do-chatbots-keep-telling-…
  3. Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] ·

    404 Media: Chatbots Keep Telling Stories About Lighthouse Keeper ‘Elias Thorne’. We Might Know Why. “In late May, researchers Sil Hamilton and David Mimno at Co

    404 Media: Chatbots Keep Telling Stories About Lighthouse Keeper ‘Elias Thorne’. We Might Know Why. “In late May, researchers Sil Hamilton and David Mimno at Cornell University’s Department of Information Science published their paper, ‘Elias in the Lighthouse, Again?’ on the pre…

  4. Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] ·

    Why do chatbots keep telling stories about someone named Elias Thorne? A new study finds AI models repeat the same character - a lighthouse keeper called Elias

    Why do chatbots keep telling stories about someone named Elias Thorne? A new study finds AI models repeat the same character - a lighthouse keeper called Elias - in 88% of generated stories. Researchers blame alignment training that created safe alternatives. https:// gizmodo.com…

    LINKS gizmodo.com/why-do-chatbots-keep-telling-…
  5. Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] ·

    Chatbots Keep Telling Stories About Lighthouse Keeper ‘Elias Thorne’. We Might Know Why https://www. 404media.co/elias-thorne-chatb ots-llms-chatgpt-lighthouse-

    Chatbots Keep Telling Stories About Lighthouse Keeper ‘Elias Thorne’. We Might Know Why https://www. 404media.co/elias-thorne-chatb ots-llms-chatgpt-lighthouse-keeper-story/ ❖ http:// BRAIN.US.COM # AI # news # press

    LINKS 404media.co/elias-thorne-chatbots-llms-ch… brain.us.com
  6. Mastodon — mastodon.social TIER_1 English(EN) · [email protected] ·

    Why Do Chatbots Keep Telling Stories About Someone Named 'Elias Thorne'? https://gizmodo.com/why-do-chatbots-keep-telling-stories-about-someone-named-elias-thor

    Why Do Chatbots Keep Telling Stories About Someone Named 'Elias Thorne'? https://gizmodo.com/why-do-chatbots-keep-telling-stories-about-someone-named-elias-thorne-2000770629 # AI # Tech # Culture

    LINKS gizmodo.com/why-do-chatbots-keep-telling-…

RELATED ENTITIES

RELATED TOPICS