Comment on LLMs are surprisingly great at compressing images and audio, DeepMind researchers find

akrot@lemmy.world ⁨9⁩ ⁨months⁩ ago

• PupBiru@kbin.social ⁨9⁩ ⁨months⁩ ago

  i’d guess they could hyper optimise for “perceived difference” rather than data loss specifically… they do a pretty good job of generating something from nothing, so i’d say with enough data they’d probably generate a pretty reasonable facsimile of “standard” stuff

  source

  • Edgelord_Of_Tomorrow@lemmy.world ⁨9⁩ ⁨months⁩ ago

    An LLM can’t know what difference a person has perceived.

    source

    • ilinamorato@lemmy.world ⁨9⁩ ⁨months⁩ ago

      There have been a lot of studies done (and published) on what humans can and can’t perceive. I wouldn’t have much trouble believing that the LLM has access to them and can pattern match on the variables involved.

      source
• BetaDoggo_@lemmy.world ⁨9⁩ ⁨months⁩ ago

  It’s lossless: arxiv.org/pdf/2309.10668.pdf

  source