you are viewing a single comment's thread
view the rest of the comments
[–] 100 points 2 years ago (20 children)

I remember when compression was popularized, like mp3 and jpg, people would run experiments where they would convert lossy to lossy to lossy to lossy over and over and then share the final image, which was this overcooked nightmare

I wonder if a similar dynamic applies to the scenario presented in the comic with AI summarization and expansion of topics. Start with a few bullet points have it expand that to a paragraph or so, have it summarize it back down to bullet points, repeat 4-5 times, then see how far off you get from the original point.

  • source
  • hideshow 20 child comments
  • [–] 54 points 2 years ago* (10 children)

    In my experience, LLMs aren't really that good at summarizing

    It's more like they can "rewrite more concisely" which is a bit different

  • source
  • parent
  • hideshow 10 child comments
  • [–] 39 points 2 years ago

    Summarizing requires understanding what's important, and LLMs don't "understand" anything.

    They can reduce word counts, and they have some statistical models that can tell them which words are fillers. But, the hilarious state of Apple Intelligence shows how frequently that breaks.

  • source
  • parent
  • [–] 23 points 2 years ago (5 children)

    I used to play this game with Google translate when it was newish

  • source
  • parent
  • hideshow 5 child comments
  • [–] 17 points 2 years ago (3 children)

    There is, or maybe was, a YouTube channel that would run well known song lyrics through various layers of translation, then attempt to sing the result to the tune of the original.

  • source
  • parent
  • hideshow 3 child comments
  • [–] 9 points 2 years ago

    translation party!

    Throw Japanese into English into Japanese into English ad nauseum, untill an 'equilibrium' statement is reached.

    ... Which was quite often nowhere near the original statement, in either language... but at least the translation algorithm agreed with itself.

  • source
  • parent
  • [–] 49 points 2 years ago (1 child)

    A couple decades ago, novelty and souvenir shops would sell stuffed parrots which would electronically record a brief clip of what they heard and then repeat it back to you.

    If you said "Hello" to a parrot and then set it down next to another one, it took only a couple of iterations between the parrots to turn it into high pitched squealing.

  • source
  • parent
  • hideshow 1 child comment
  • [–] 11 points 2 years ago* (3 children)

    i was curious so i tried it with chatgpt. here are the chat links:

    overall it didn't seem too bad. it sort of started focusing on the ecological and astrobiological side of the same topic but didn't completely drift. to be honest, i think it would have done a lot worse if i made the prompt less specific. if it was just "summarize this text" and "expand on these points" i think chatgpt would get very distracted

  • source
  • parent
  • hideshow 3 child comments
  • [–] 4 points 2 years ago

    Interesting. I also wonder how it would fare across different models (eg user a uses chatgpt, user b uses gemini, user c uses deepseek, etc) as that may mimic real world use (such as what’s depicted in the comic) more closely

  • source
  • parent