79
I Told My AI Job Interviewer I Love You (www.youtube.com)
submitted 1 week ago by to c/funny@sh.itjust.works
14 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] [S] 22 points 1 week ago (4 children)

I assume there's a second AI that does transcription. Or maybe it's the same one. There's probably a summary and a transcription and a recording.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 4 child comments
    •
  • [–] 9 points 1 week ago (3 children)

    As a lay person with a modicum of interest in how these work, I'm vaguely aware that the modern paradigm (like with the cat farted) is to have multiple "specialized" models working in tandem called by the main thinking model.

    There's probably a model doing the transcription, one doing a summary of the transcription, another being fed the summary to rephrase it according to the recruitment office's instructions, et cetera. That's on top of what I count as at least 5 models working in tandem for the interview itself (voice, video, "thinking", emotion, memory).

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 3 child comments
    •
  • [–] [S] 5 points 1 week ago (2 children)

    Wow, I didn't realize that they were that specialized now. That makes a lot more sense than the One Big Model That Can Do Everything.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] 3 points 1 week ago*

    Even when it's "one big model" that "model" has usually been a moe for the last couple of years. Which is several smaller models in a trench coat. They each respond and the result you see is an amalgam.

  • permalink
  • fedilink
  • source
  • parent
  • [–] 3 points 1 week ago

    I don't want to oversell my understanding of the topic, but I think at least the big corpo chatbots have the resources to run them entirely separately like that. I'm not sure how smaller models are compressed down or if they're able to staple some of these specialist models into the main ones to make the One Big Model That Can Do Everything. Apparently text-based models are capable of doing image now so maybe they can?

  • permalink
  • fedilink
  • source
  • parent