Comment on Scientists discover that feeding AI models 10% 4chan trash actually makes them better behaved

• General_Effort@lemmy.world ⁨1⁩ ⁨week⁩ ago

  en.wikipedia.org/wiki/GPT4-Chan

  source

  • Natanael@infosec.pub ⁨1⁩ ⁨week⁩ ago

    I remember this lol

    Tldr neural network models are incredibly weird. My best guess is that the combination of common recurring structure with variations based on common rules (joke threads and all) helps the model derive some intuition about how to handle variations of things.

    Also reminds me of an even earlier neutral network which got better at playing specific games after being trained on large amounts of text completely unrelated to the game, like encyclopedias or whatever.

    source
• semperverus@lemmy.world ⁨1⁩ ⁨week⁩ ago

  There’s a “your mom” joke here but I’m not going to make it because you don’t deserve that.

  source

  • Kolanaki@pawb.social ⁨1⁩ ⁨week⁩ ago

    I am not sure if you and @General_Effort got the reference I was making, and I just wanna share it for everyone else who might not have seen it yet because it’s great:

    Image

    source

    • semperverus@lemmy.world ⁨1⁩ ⁨week⁩ ago

      I can’t believe I forgot about this greentext. I knew it but didn’t catch it… I apologize

      source