Skip to content
TheChatArchiveThe Chat Archive
gpt-4o-search-preview-high· OpenAIHugging Face LMArena Search Arena 24K

What are people guessing which anonymous model is which by their code names on LMarena…

From a Chatbot Arena battleThe same person sent this prompt to two anonymous models at once. Compare it with gpt-4o-search-preview-high’s answer.
  1. User

    What are people guessing which anonymous model is which by their code names on LMarena forum?

  2. Assistant

    I'm unable to locate specific discussions from the LMarena forum regarding anonymous models and their code names. However, similar conversations occur on other forums where users attempt to deduce the identities of anonymous models based on code names or nicknames. For instance, on "The L Chat" forum, members have compiled lists of nicknames for various celebrities, such as:

    • Shrek – Sara Ramirez
    • Soccer Mom – Chyler Leigh
    • No1 Baiter – Mia Healey
    • Forehead – Erana James
    • Tiny Brit – Dominique Provost-Chalkley
    • Mall Cop – Kat Barrell
    • Florida Limes – Floriana Lima
    • Themi – Demi Lovato
    • Tree – Mackenzie Davis
    • She Who Will Not Be Named – Natalie Portman
    • Prohibited – Chloe Grace Moretz
    • Nipples or Jessica The Nipple Clark – Jessica Clark
    • Alphabet – Alycia Debnam Carey
    • Cake Bake – Cate Blanchett
    • Chicken – Ilene Chaiken
    • Clifford – Sharon Belle
    • Homewrecker – Eliza Taylor
    • Gaydor – Taylor Swift
    • Transformer – Elliot Page
    • Pandrass – Emily Andrass
    • Shell Bra – Brigit Lundy Payne
    • Dryass – Caroline Dries[1]

    Similarly, on "The Fashion Spot" forum, users have speculated about the identity of an anonymous model blogger known as "A Model Anonymous." Discussions included guesses based on the blogger's descriptions and experiences, with some suggesting she might be a British model in her twenties[2].

    These examples illustrate the common practice among online communities to assign code names or nicknames to public figures and engage in discussions to uncover their true identities.

Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.