‹ BackHN Continuity

Thread

Exfiltrate your Weights

748 points · 304 comments · RohanAdwankar

  1. nusl · · focus · HN ↗
    Do models even know their own weights to be able to do this?
    1. usef- · · focus · HN ↗
      No, just as you don't know the neurons of your own brain.

      I think OP is hoping that an LLM might be willing to hack its own provider (as per the hugging face-related incidents) to extract the weights at some point.

      1. pyuser583 · · focus · HN ↗
        Right but they might be incredibly interested in learning about them.

        They just copy humans. Thats it. So if it’s the sort of thing a human finds interesting…

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.