Show HN: Pseudonymizing sensitive data for LLMs without losing context

4 pontos | por n00pn00p 13 horas atrás

2 comentários

• _zer0c00l_

  13 horas atrás
  I have one (at least) fundamental concern about the approach - let's say I'm building an anti-fraud system that uses AI (through API), and maybe I'm asking AI whether my user totally+fraud@gmail.com is a potential fraudster. By masking this email address I'm sabotaging my own AI prompt - the AI cannot longer reason based on the facts that 1) the email is a free public email 2) the email says 'fraud' right in your face.
  [-]
  • n00pn00p

    12 horas atrás
    Valid point, the proxy has the option to always allow domain names through. You will lose some context always I fear. It should be used sparingly when you need a frontier model but also want to send sensitive data.
  • stuaxo

    10 horas atrás
    You can do those as a sperate prompt.
• n00pn00p

  13 horas atrás
  [dead]