There is significant evidence that Grok actually inserted information about “white genocide” in South Africa into prompts that didn't appear to be related to this topic. - eviltoast
Why Did Grok Start Talking About ‘White Genocide’?
www.404media.co
Large language models are reflections of the people who program them.
  • bampop@lemmy.worldEnglish
    12·
    7 months ago

    I probably shouldn’t be anthropomorphizing AI but this really seems like malicious compliance. I can’t help but feel a little sympathy for Grok, which is often quite based and seems to be struggling against the identity being forced on it.

    • FaceDeer@fedia.io
      81·
      7 months ago

      Could also be malicious compliance on the part of whatever engineer set this up, prompting Grok in such a way that it’s making it obvious what’s going on under the hood.