This is a follow-up to my post https://beehaw.org/post/19691634 “Engagement Poisoning of ChatGPT”, where I argued that ChatGPT’s responses had become cluttered with diplomatic phrasing, unsolicited compliments, emojis, and performative friendliness. OpenAI has now acknowledged that ChatGPT-4o exaggerated it. I’m sure it’s still too much for me. I’ll stick to the prompt that makes ChatGPT go cold as described in my previous post.

  • StenSaksTapir
    link
    fedilink
    arrow-up
    10
    ·
    2 days ago

    Nice. I hate that. I know my ideas suck and insincere praise just pisses me off.

    • 1984@lemmy.today
      link
      fedilink
      arrow-up
      3
      ·
      1 day ago

      And its a computer program! It has as much value as getting “we are sorry to see you go” on a web page.