Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Here's what I got in different models:

GPT-4o: "Aldric" (male)

o1-preview: "Elara" (female)

4o-mini: "Lila" (female)

GPT-4 (legacy): "Elinor" (female)

Four different models, four different names. But one of them was Elara -- and, interestingly, it was in the latest model.



Google’s Gemma seems infected too:

  $ ollama run gemma2
  >>> Tell me a story.
  The old lighthouse keeper, Silas, squinted at the horizon. […]
  >>> /clear
  Cleared session context
  >>> Tell me a story.
  The old woman, Elara, […]
Hmm. Hmm.

Tried llama3.2 too. Gave me a Luna in the mountains twice (almost identical), then a Madame Dupont, then a different Luna in Tuscany twice (almost identical), then Pierre the old watchmaker. llama3.2:1b branched out a little further, to Alessandro in France and Emrys in a far-off land, but then looped back to Luna in the mountains.

(And yes, I was clearing the session each time.)


GPT has some self understanding. On asking why it uses that name, it at least gave the type of qualities correctly.

> It sounds like you're referring to a story or narrative that I've generated or discussed involving a character named Aldric. If this is the case, Aldric would likely be used as a character who embodies leadership, wisdom, or noble traits due to the name's meaning and historical connotations. Characters named Aldric might be portrayed as experienced leaders, wise sages, or key figures in a fantasy or historical context.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: