Comment on GenAI tools are acting more ‘alive’ than ever; they blackmail people, replicate, and escape

just_another_person@lemmy.world ⁨4⁩ ⁨days⁩ ago

• Mr_Peartree@lemmy.world ⁨4⁩ ⁨days⁩ ago

  So you’re suggesting that there should be no controls to prevent those commands?

  source

  • just_another_person@lemmy.world ⁨3⁩ ⁨days⁩ ago

    No, I’m saying that they are trained to do these things. Neural net and frameworks are fast sorting algorithmic relations between things, so…fast search+reduce.

    There is no novel ideation in these things.

    Don’t train them to do that thing, and they won’t do that thing. They didn’t just “decide” to try and jailbreak themselves.

    source
  • Dasus@lemmy.world ⁨4⁩ ⁨days⁩ ago

    The pop-up windows on porn-sites back in 2000 were self-replicating, yet here we are.

    (Yes I know there’s a difference, but the difference is probably way smaller from those popups to LLM’s than LLM’s to AGI.)

    source
  • givesomefucks@lemmy.world ⁨4⁩ ⁨days⁩ ago

    It’s a fundamental flaw in how they train them.

    Like, have you heard about how slime mold can map out more efficient public transport lines than human engineers?

    That doesn’t make it smarter, it’s just finding the most efficient paths between resources.

    With AI, they “train” it by trial and error, and the resource it’s concerned about is how long a human engages. It doesn’t know what it’s doing, it’s not trying to achieve a goal.

    It’s just a mirror that uses predictive test to output whatever text is most likely to get a response. And just like the slime mold is better at a human at mapping optimal paths between resources, AI will eventually be better at getting a response from a human, unless Dead Internet becomes true and all the bots just keep engaging with other bots.

    Because of it’s programming, it won’t ever disengage, bots will just get in never ending conversations with each, achieving nothing but using up real world resources that actual humans need to live.

    That’s the true AI worst case scenario, it ain’t even going to turn everything into paperclips. It’s going to burn down the planet so it can argue with other chatbots over conflicting propaganda. Or even worse just circle jerk itself.

    Like, people think chatbots are bad, once AI can can make realistic TikToks we’re all fucked. Even just a picture is 1,000x the resources as a text reply. 30 second slop videos are going to be disastrous once an AI can output a steady stream

    source

    • hisao@ani.social ⁨3⁩ ⁨days⁩ ago

      and the resource it’s concerned about is how long a human engages.

      Why do you think models are trained like this? To my knowledge most LLMs are trained on giant corpuses of data scraped from internet, and engagement as a goal or a metric isn’t in any way embedded inherently in such data. It is certainly possible to train AI for engagement but that requires completely different approach: they will have to gather giant corpus of interactions with AI and use that as a training data. Even if new OpenAI models use all the chats of previous models in training data with engagement as a metric to optimize, it’s still a tiny fraction of their training set.

      source

      • givesomefucks@lemmy.world ⁨3⁩ ⁨days⁩ ago

        www.sciencedirect.com/…/S0268401225000507

        But just in general…

        This is America, you think any of this tech companies wouldn’t try to maximize engagement?

        That’s just wild in 2025 bro

        source
    • Mr_Peartree@lemmy.world ⁨3⁩ ⁨days⁩ ago

      Thank you for this comment. I was very hyperbolic in my reference to Skynet and I take ownership of that. Bad joke on my part, but I’ll take the downvotes along with it.

      Will there be a need for more controls in the future? Absolutely! Right now they’re largely behind a terminal and a machine we can control. But what about drones or non-humanoid bots? Then there’s a case for undue harm

      source