AI generated issue

Comments

• AmbiguousProps@lemmy.today ⁨1⁩ ⁨week⁩ ago

  Why do LLMs obsess over making numbered lists? They seem to do that constantly.

  source

  • Tolookah@discuss.tchncs.de ⁨1⁩ ⁨week⁩ ago

    Oh, I can help! 🎉

    1. computers like lists, they organize things.
    2. itemized things are better when linked! 🔗
    3. I hate myself a little for writing this out 😐

    source
  • coherent_domain@infosec.pub ⁨1⁩ ⁨week⁩ ago

    My conspricy is that they have a hard time figuring out the logical relation between sentenses, hence do not generate good transitions between sentences.

    I think bullet point is manually tuned up by the developers instead of inheritly in the model, because we don’t tend to see them that much in human communications.

    source

    • possiblylinux127@lemmy.zip ⁨1⁩ ⁨week⁩ ago

      That’s not a bad theory

      source
  • gamer@lemm.ee ⁨4⁩ ⁨days⁩ ago

    Late but I’m pretty sure it’s a byproduct of the RHLF process used to train these types of models. Basically, they have a bunch of humans look at multiple outputs from the LLM and rate the best ones, and it turns out people find lists easier to understand than other styles (alternatively, the poor souls slaving away in the AI mines rating responses all day find it faster to understand a list than a paragraph through the blurry lens of mental fatigue)

    source
  • possiblylinux127@lemmy.zip ⁨1⁩ ⁨week⁩ ago

    • Honestly I don’t know

    source
  • A_norny_mousse@feddit.org ⁨1⁩ ⁨week⁩ ago

    Well they are computers…

    source
• DudeDudenson@lemmings.world ⁨1⁩ ⁨week⁩ ago

  I wonder if they made chat gpt use an unnatural amount of emojis just to make it easier to spot

  source

  • qaz@lemmy.world ⁨1⁩ ⁨week⁩ ago

    People often use a ridiculous amount of emoji’s in their readme, perhaps seeing it was a README triggered something in the LLM to talk like a readme?

    source
• FQQD@lemmy.ohaa.xyz ⁨1⁩ ⁨week⁩ ago

  Wow, this just hurts. The “twice, I might add!” is sooooo fucking bad. I don’t have aby words for this.

  source

  • dabaldeagul@feddit.nl ⁨1⁩ ⁨week⁩ ago

    aby

    Checks out

    source

    • FQQD@lemmy.ohaa.xyz ⁨1⁩ ⁨week⁩ ago

      god damn it i can’t type lmao

      source
• possiblylinux127@lemmy.zip ⁨1⁩ ⁨week⁩ ago

  There have been so many people filing AI generated security vulnerabilities

  source
• salmoura@lemmy.eco.br ⁨1⁩ ⁨week⁩ ago

  The emoji littering actually drove me away from using fastapi while reading its documentation.

  source
• Korne127@lemmy.world ⁨1⁩ ⁨week⁩ ago

  I mean, even if it’s annoying someone obviously used AI, they probably still have that problem and just suck at communicating that themselves

  source

  • qaz@lemmy.world ⁨1⁩ ⁨week⁩ ago

    They don’t, because it’s not an actual issue for any human reading it. The README contains the data and the repo is just for coordination, but the LLM doesn’t understand that.

    source

    • Korne127@lemmy.world ⁨1⁩ ⁨week⁩ ago

      Then… that’s so fucking weird, why would someone make that issue? I genuinely lack the understanding for how this could have happened in that case.

      source

      • -> View More Comments