Edit to add: I also found someone who recorded a voice chat of the same thing. This isn't that someone uploaded a song, or that AI didn't actually process the file. These models really are this sycophantic:

https://m.youtube.com/shorts/JqvDLHshTtI

you are viewing a single comment's thread
view the rest of the comments
[–] 4 points 7 months ago (3 children)

I wonder if they actually linked it to an algorithm that analyses the sound that is looking for certain patterns or something, and that is why you get the "atmosphere piece" thing.

  • source
  • hideshow 3 child comments
  • [–] 5 points 7 months ago (2 children)

    According to their tech/marketing papers, it's supposedly multi-modal, encoding audio to tokens.

  • source
  • parent
  • hideshow 2 child comments
  • [–] 2 points 7 months ago (1 child)

    yeah but that doesn't mean anything, does it? I don't think they just tokenize the raw audio, that wouldn't make sense, right?

  • source
  • parent
  • hideshow 1 child comment