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

• Natanael@infosec.pub ⁨2⁩ ⁨weeks⁩ 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