Comment on Resume Tip: Hacking "AI" screening of resumes

YurkshireLad@lemmy.ca ⁨11⁩ ⁨months⁩ ago

• GammaGames@beehaw.org ⁨11⁩ ⁨months⁩ ago

  It would probably be through a third party service that uses chatgpt

  source
• clay_pidgin@sh.itjust.works ⁨11⁩ ⁨months⁩ ago

  I don’t think the models absorb new information from questions, do they?

  source

  • YurkshireLad@lemmy.ca ⁨11⁩ ⁨months⁩ ago

    I’d be surprised if they didn’t, to be honest.

    source
  • Enkers@sh.itjust.works ⁨11⁩ ⁨months⁩ ago

    They do not. My understanding is that the models are static.

    source

    • Infinite@lemmy.zip ⁨11⁩ ⁨months⁩ ago

      Their settings imply that they do

      Image

      source

      • Enkers@sh.itjust.works ⁨11⁩ ⁨months⁩ ago

        I guess I should be a bit more specific. There’s no feedback loop into the currently running model. They could use that data to tune or train future versions of the model, but there’s no mechanism to live update the model weights in place. Or at least not to my knowledge.

        The only things that’ll make a difference in the same version of the model are the system prompt, context window and prompt.

        source
  • invisiblegorilla@sh.itjust.works ⁨11⁩ ⁨months⁩ ago

    Yeah, its still trained on the data it’s fed

    source