How Googlers cracked OpenAI's ChatGPT with a single word
www.sfgate.com
A research team from Bay Area tech giant Google got OpenAI's ChatGPT to spit out its private training data in a new study.

Basically: you ask for poems forever, and LLMs start regurgitating training data:

    • inspxtr@lemmy.worldEnglish
      3·
      10 个月前

      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.