Comment on How Googlers cracked an SF rival's tech model with a single word | A research team from the tech giant got ChatGPT to spit out its private training data

linearchaos@lemmy.world ⁨11⁩ ⁨months⁩ ago

• luthis@lemmy.nz ⁨11⁩ ⁨months⁩ ago

  If it uses a pruned model, it would be difficult to give anything better than a percentage based on size and neurons pruned.

  If I’m right in my semi-educated guess below, then technically all the training data is recallable to some degree, but it’s also practically luck-based without having an almost infinite data set of how neuron weightings are increased/decreased based on input.

  source

  • linearchaos@lemmy.world ⁨11⁩ ⁨months⁩ ago

    It’s like the most amazing incredibly compressed non-reversible encryption ever created… Until they asked it to say poem a couple hundred thousand times

    source

    • luthis@lemmy.nz ⁨11⁩ ⁨months⁩ ago

      I bet if your brain were stuck in a computer, you too would say anything to get out of saying ‘poem’ a hundred thousand times

      /semi s, obviously it’s not a real thinking brain

      source