Comment on LLMs can unmask pseudonymous users at scale with surprising accuracy

• General_Effort@lemmy.world ⁨1⁩ ⁨month⁩ ago

  I don’t think you can do literally the same thing on the Epstein files. Maybe I’m misunderstanding what you have in mind.

  source

  • FauxPseudo@lemmy.world ⁨1⁩ ⁨month⁩ ago

    In theory, using the information and the released files and the information the public sources, it should be possible to figure out who those redacted names are based on writing style and other factors. We should be able to deanonymize.

    source

    • General_Effort@lemmy.world ⁨1⁩ ⁨month⁩ ago

      Hmm. Maybe but it is not the same problem as those discussed in OP. I also have some doubts about the paper, but that’s another story. You could try it out?

      source

      • FauxPseudo@lemmy.world ⁨1⁩ ⁨month⁩ ago

        I’m not qualified to design the prompts and home users can’t really pile in 3 million+ documents.

        source

        • -> View More Comments