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

bloopernova@programming.dev ⁨1⁩ ⁨year⁩ ago

• luthis@lemmy.nz ⁨1⁩ ⁨year⁩ ago

  I think this might be intrinsic. Like, there isn’t a way to fix this.

  source
• Stelus42@lemmy.ca ⁨1⁩ ⁨year⁩ ago

  Well something certainly seems to have been done Image

  source

  • inspxtr@lemmy.world ⁨1⁩ ⁨year⁩ ago

    Something like this, unless they know the root cause (I didn’t read the paper so not sure if they do), or something close to it, may still be exploitable.

    source