Albuquerque, New Mexico

    • Xanthrax@lemmy.worldOP
      link
      fedilink
      arrow-up
      15
      ·
      edit-2
      3 days ago

      That is how language models and text to speech work. Most language learning models hit a text limit, read over the last inquiry, and figure out based on that and your input, how to respond/ perpetuate the conversation. They can’t “remember” what they said in the past. It starts “hallucinating” when the “conversation” diverges too much. You can also waste their tokens by forcing it produce text, images, etc… The whole idea is that you’re wasting their investment to scam people.

        • Xanthrax@lemmy.worldOP
          link
          fedilink
          arrow-up
          2
          ·
          3 days ago

          30 cents a minute. If you want to hit them hard, use multiple voips and a recording of yourself.

          • kibblebits@quokk.au
            link
            fedilink
            English
            arrow-up
            3
            arrow-down
            12
            ·
            3 days ago

            That’s not how AI works. But you entertain yourself fighting AI one token at a time.

            • Xanthrax@lemmy.worldOP
              link
              fedilink
              arrow-up
              2
              ·
              edit-2
              3 days ago

              You can use as many voips as you want. Buying tokens is a lot more expensive than hosting an automated voice call on your computer.

                • Xanthrax@lemmy.worldOP
                  link
                  fedilink
                  arrow-up
                  1
                  ·
                  edit-2
                  3 days ago

                  Hell yeh. If you know any older people in your family using social services, call their social serves number one digit off. I’m making a bot for that rn. I’m going to try self host and use our solar pannels to keep it self-sufficient