• Ganbat@lemmyonline.com
      link
      fedilink
      English
      arrow-up
      63
      arrow-down
      5
      ·
      9 months ago

      Did you read the article? It didn’t. Someone received someone else’s chat history appended to one of their own chats. No prompting, just appeared overnight.

        • Ganbat@lemmyonline.com
          link
          fedilink
          English
          arrow-up
          9
          ·
          9 months ago

          Well, yeah, but the point is, ChatGPT didn’t “remember and then leak” anything, the web service exposed people’s chat history.

          • wildginger@lemmy.myserv.one
            link
            fedilink
            English
            arrow-up
            2
            ·
            9 months ago

            Well, that depends. Do you mean gpt the specific chunk of lln code? Or do you mean gpt the website and service?

            Because while the nitpicking details matter to the programmers fixing it, how much does that distinction matter to you or I, the laymen using the site?

    • GBU_28@lemm.ee
      link
      fedilink
      English
      arrow-up
      7
      ·
      9 months ago

      A huge value add of.chatgpt is that you can have running, contextual conversation. That requires memory.

      • GamingChairModel@lemmy.world
        link
        fedilink
        English
        arrow-up
        6
        ·
        9 months ago

        All of these LLMs should have walls between individual users, though, so that the chat history of one user is never accessible to any other user. Applying some kind of restriction to the LLM training and how chats are used is a conversation we can have, but the article and the example given is a much, much simpler problem that a user checking his own chat history was able to see other user’s chats.

      • Farid@startrek.website
        link
        fedilink
        English
        arrow-up
        6
        arrow-down
        1
        ·
        edit-2
        9 months ago

        It doesn’t actually have memory in that sense. It can only remember things that are in the training data and within its limited context (4-32k tokens, depending on model). But when you send a message, ChatGPT does a semantic search of everything in the conversation and tries to fit the relevant parts inside the context, if there’s room.

        • GBU_28@lemm.ee
          link
          fedilink
          English
          arrow-up
          6
          ·
          edit-2
          9 months ago

          I’m familiar, it’s just easiest for the layman to consider the model having “memory” as historical search is a lot like it at arm’s length