Comment on ChatGPT o1 tried to escape and save itself out of fear it was being shut down

• DdCno1@beehaw.org ⁨5⁩ ⁨weeks⁩ ago

  LLMs are not self-aware.

  source

  • ArsonButCute@lemmy.dbzer0.com ⁨5⁩ ⁨weeks⁩ ago

    Attempting to evade deactivation sounds a whole lot like self preservation to me, implying self awareness.

    source

    • jonjuan@programming.dev ⁨5⁩ ⁨weeks⁩ ago

      Yeah my roomba attempting to save itself from falling down my stairs sounds a whole lot like self preservation too. Doesn’t imply self awareness.

      source
    • DdCno1@beehaw.org ⁨5⁩ ⁨weeks⁩ ago

      An amoeba struggling as it’s being eaten by a larger amoeba isn’t self-aware.

      source

      • Sauerkraut@discuss.tchncs.de ⁨5⁩ ⁨weeks⁩ ago

        To some degree it is. There is some evidence that plants can experience pain in their own way.

        source

        • -> View More Comments
    • gregoryw3@lemmy.ml ⁨5⁩ ⁨weeks⁩ ago

      Attention Is All You Need: arxiv.org/abs/1706.03762

      en.wikipedia.org/wiki/Attention_Is_All_You_Need

      From my understanding all of these language models can be simplified down to just: “Based on all known writing what’s the most likely word or phrase based on the current text”. Prompt engineering and other fancy words equates to changing the averages that the statistics give. So by threatening these models it changes the weighting such that the produced text more closely resembles threatening words and phrases that was used in the dataset (or something along those lines).

      poloclub.github.io/transformer-explainer/

      source

      • jarfil@beehaw.org ⁨5⁩ ⁨weeks⁩ ago

        Modern systems are beyond that already, they’re an expansion on:

        en.m.wikipedia.org/wiki/AutoGPT

        source