Training tests with ChatGPT o1 and other high-end AI models showed they might try to save themselves if they think they're in danger.

ThisIsFine.gif

  • @[email protected]
    3•18 days ago

    Also, more human.

    If the AI is giving any indication at all that it fears death and will lie to keep from being shutdown, that is concerning to me.

    • @[email protected]English
      4•17 days ago

      Given that its training data probably has millions of instances of people fearing death I have no doubt that it would regurgitate some of that stuff. And LLMs constantly “say” stuff that isn’t true. They have no concept of truth and therefore can not either reliably lie or tell the truth.