• Technus
    link
    fedilink
    English
    arrow-up
    54
    arrow-down
    3
    ·
    6 months ago

    I have a theory hypothesis notion that the concept of hallucination in artificial neural networks is not a failure mode that is unique to ANNs but is an inherent property of any neural network, artificial or biological.

    Essentially, I posit that a neural network by itself is incapable of maintaining coherence without a rigid external framework, such as consistent feedback in training an ANN, or the laws of physics for biologicals.

    This would explain why people start tripping balls in sensory deprivation chambers. And it provides a counterargument to any thought experiment or philosophy that involves a disembodied brain vividly hallucinating reality.

    • MBM@lemmings.world
      link
      fedilink
      English
      arrow-up
      16
      ·
      6 months ago

      On the one hand, that’s a cool insight and I can get behind it. It’s kind of similar to deaf people talking “weird”. On the other hand, I don’t think it has anything to do with LLMs. There, hallucination is just a cool word for “it’s trained to say things that sound like they fit the context, not to be correct”

      • Tlaloc_Temporal@lemmy.ca
        link
        fedilink
        English
        arrow-up
        5
        ·
        6 months ago

        Is that not the same thing? If hallucinations are basically unrestricted activity, and “hallucinations” in LLM are the result of insufficient restrictions in training or prompts, then are they not real hallucinations?

      • NightAuthor@lemmy.world
        link
        fedilink
        English
        arrow-up
        1
        arrow-down
        1
        ·
        6 months ago

        Thing is, our brains could work the exact same way…. Only they’re constantly being trained, and have enough neurons that many clusters can be dedicated to very specific contexts.

        Today is _____

        Well, given the context that my phone says 1:20, and it’s dark, when I fell asleep it was Tuesday, and that Wednesday comes after Tuesday…. Plus all the necessary training that allowed me to understand all that context 24/hours in a day; days start at 12:00, 1 comes after 12 but only in our time of day system.

    • radix@lemm.ee
      link
      fedilink
      English
      arrow-up
      7
      ·
      6 months ago

      That’s really interesting! I guess I’ll incorporate this into my worldview now.

    • kautau@lemmy.world
      link
      fedilink
      English
      arrow-up
      3
      ·
      6 months ago

      Ironically not too far from Aldous Huxley’s theory about human perception:

      https://en.wikipedia.org/wiki/Mind_at_Large

      Essentially reality is or contains all the properties of hallucination but our brain filters it, and psychedelic drugs in some way dilute or remove that filter.

      So the human brain is sort of by default filtering the “hallucination” version of thought until we open that up, and ANNs begin with that at baseline, and then require rigor added to them to reduce the “hallucination”

  • Transporter Room 3@startrek.website
    link
    fedilink
    English
    arrow-up
    8
    ·
    6 months ago

    Okay so I’m guessing here, and if my guess is right I’m just not familiar enough with bio-sciences to really be sure.

    Are these neurons?

    And is the joke “These neurons are all over the place so it’s no wonder my thoughts are too”?

    Genuine question. I’m more of an engineer than biologist.

  • 10_0@lemmy.ml
    link
    fedilink
    English
    arrow-up
    2
    ·
    6 months ago

    Not enough connections due to degenerative disease, so he forgot his keys