A technique used by Google researchers to reveal ChatGPT training data is now banned by OpenAI.
  • Nawor3565@lemmy.blahaj.zoneEnglish
    2·
    11 months ago

    What if you just told it to exit on n = -1? If it only increments n, it should also go on forever (or, hell, just try a really big number for n)

    • Sanctus@lemmy.worldEnglish
      2·
      11 months ago

      That might work if it doesn’t attempt to correct it to something that makes sense. Worth a try tbh.