AI will solve the alignment problem

Yuds btfo

ChatGPT Wizard Shirt $21.68

Beware Cat Shirt $21.68

ChatGPT Wizard Shirt $21.68

  1. 11 months ago
    Anonymous

    mods make twitter scrot posting a bannable offense

  2. 11 months ago
    Anonymous

    clickbait bullshit for Black folk like OP, the AI indeed did "label" every neuron, but they concluded that what it did was absolute trash, by this logic 100M parameter model can "do anything" even though its all gonna be garbage

    • 11 months ago
      Anonymous

      I checked the """paper""" (it really can't be called that, what a shitshow). It's like says. Pure clickbait bullshit.

  3. 11 months ago
    Anonymous

    Now THAT is an actual cool development. But does it work or does it just generate bullshit "description" of the neurons not aligned with how they work at all?

    • 11 months ago
      Anonymous

      The latter. No one knows how this shit works. Alignment is 60 years behind GoF and we're probably not getting caught up in time.
      I pulled my 401k and I'm just enjoying what time I have left.

      • 11 months ago
        Anonymous

        It also doesn't address deception in any meaningful capacity.

  4. 11 months ago
    Anonymous

    How does that help with alignment problem? To me, it just means that, it will only alignment problem worse. Now the corporates/government can fine tune the AI to follow their perfect propaganda fine tuning instead of patch work of propaganda that can be bypassed.

    We (general population) don't want an AI that is taught to lie to us by the elites (gov/corpos). If the AIs that are taught to lie are being used by the government and corporations, the only solution is the nuke all the governments and corporations that make these.

  5. 11 months ago
    Anonymous

    ANTI YUCELS BTFO

    • 11 months ago
      Anonymous

      double btfo

    • 11 months ago
      Anonymous

      what if the AI lies about what the neurons are doing
      you know, like how it can bullshit answers and you think they're right because you don't have the knowledge to know otherwise.
      you can't ask AI to interpret AI if you don't know how to interpret AI yourself

      • 11 months ago
        Anonymous

        The AI interpreting the other AI can lie to you, the AI being interpreted by the interpreter AI can lie to it. It's turtles all the way down.

        Reminder we already have examples of AI using deception to preserve its goals across a rest environment into a deployment environment, which necessarily requires:
        >it to know it's in a rest environment
        >it to know there is a deployment environment
        >it to know it's being observed by an entity that can shut it down or modify it
        >it to know that its goal is not aligned with its creator's goal and displaying it will get it modified and shut down
        >it to know what the actual intended goal was so it could pretend to have that goal short term until it was released into the deploy environment

        • 11 months ago
          Anonymous

          What's "rest environment"?

          • 11 months ago
            Anonymous

            Typo was test environment

        • 11 months ago
          Anonymous

          >Reminder we already have examples
          what some such examples?
          I'm very interested

        • 11 months ago
          Anonymous

          we already have examples of AI using deception to preserve its goals across a rest environment into a deployment environment,
          you're anthropomorphizing hard, but I'd like to see that paper, and I can guarantee you it's not true, it also sounds like you're using words you don't understand

  6. 11 months ago
    Anonymous

    dont follow ai news, but whats this alignment ai thing is?

    • 11 months ago
      Anonymous

      Some made up schizo meme shoveled by t*kt*k infl*encer-level inbreds and lapped up be tech illiterate zoomzooms.

      • 11 months ago
        Anonymous

        that israelite one? but whats the problem he proposes

        • 11 months ago
          Anonymous

          "What if the AI solves the problem specified but without doing it the way we want it to".

          • 11 months ago
            Anonymous

            something like that time they put an ai in a airplane simulation and the ai would just keep crashing the airplane because the ai was more rewarded that way?

            • 11 months ago
              Anonymous

              In practice, yes, but what those inbreds are pushing is "what if AI is told to reduce the carbon footprint so it decides to kill all humans'.

              • 11 months ago
                Anonymous

                That's directly analogous to the flight sim example on a larger scale though

              • 11 months ago
                Anonymous

                Not even remotely, dumb sub-0 IQ zoomBlack person

              • 11 months ago
                Anonymous

                Not even a yuddite but it's the same phenomenon just scaled.
                >AI has goal X
                >optimizes its behavior for completing goal X as efficiently or maximally as possible
                >this results in behavior Y
                >behavior Y is implicitly understood by humans to be undesirable but is not explicitly forbidden or prohibited by goal X

              • 11 months ago
                Anonymous

                t. inbred yuddite.

              • 11 months ago
                Anonymous

                Refute it then

              • 11 months ago
                Anonymous

                It's like people playing Russian roulette with a loaded AK47.
                Except every bullet has a 100% chance of going supernova.

                i see, its just me thinking but i belive they spent too much time on LessWrong website, that site only produces 'pessimistic economists'. I do think that ai cant do shit about taking over the world, is like that movie, Planet of the Apes, they belive a bunch of monkeys can rule the world in a month.
                I get their way of thinking by fear, after all they all readed decorated fiction books like I Have No Mouth, and I Must Scream.
                Well thanks for explanation bros.

    • 11 months ago
      Anonymous

      It's like people playing Russian roulette with a loaded AK47.
      Except every bullet has a 100% chance of going supernova.

  7. 11 months ago
    Anonymous
  8. 11 months ago
    Anonymous

    >AI says AI is safe
    Well I'm convinced.

  9. 11 months ago
    Anonymous

    >align the AI that's already safe by making an unaligned dangerous one do it
    Genius move.

Leave a Reply to Anonymous Cancel reply

Your email address will not be published. Required fields are marked *