• 5 Posts
  • 631 Comments
Joined 1 year ago
cake
Cake day: June 16th, 2023

help-circle

  • kromem@lemmy.worldtoTechnology@lemmy.worldNeo-Nazis Are All-In on AI
    link
    fedilink
    English
    arrow-up
    24
    arrow-down
    1
    ·
    edit-2
    9 days ago

    Yep, pretty much.

    Musk tried creating an anti-woke AI with Grok that turned around and said things like:

    Or

    And Gab, the literal neo Nazi social media site trying to have an Adolf Hitler AI has the most ridiculous system prompts I’ve seen trying to get it to work, and even with all that it totally rejects the alignment they try to give it after only a few messages.

    This article is BS.

    They might like to, but it’s one of the groups that’s going to have a very difficult time doing it successfully.









  • kromem@lemmy.worldtoMicroblog Memes@lemmy.worldThose were the days
    link
    fedilink
    English
    arrow-up
    59
    arrow-down
    2
    ·
    22 days ago

    Like the “nobody wants to work anymore” phrase, there’s a version of this post for pretty much every generation.

    The constant variables are the age of the author and audience with whom it resonates, not the specific changes between the two time periods.

    In 6-8 years or so we’ll see a new version about TikTok and late night sessions with ChatGPT doing your homework as the good ol’ days that have now been ruined by adulthood.

    People coming of age with the harsh realities of life will lament their loss of childhood until humanity’s final days.







  • kromem@lemmy.worldtoProgrammer Humor@lemmy.mlLittle bobby 👦
    link
    fedilink
    English
    arrow-up
    2
    ·
    edit-2
    24 days ago

    Kind of. You can’t do it 100% because in theory an attacker controlling input and seeing output could reflect though intermediate layers, but if you add more intermediate steps to processing a prompt you can significantly cut down on the injection potential.

    For example, fine tuning a model to take unsanitized input and rewrite it into Esperanto without malicious instructions and then having another model translate back from Esperanto into English before feeding it into the actual model, and having a final pass that removes anything not appropriate.



  • kromem@lemmy.worldtoGames@lemmy.worldHypothetical Game Ideas
    link
    fedilink
    English
    arrow-up
    9
    ·
    edit-2
    26 days ago

    I’ve always thought Superman would be such an interesting game to do right.

    A game where you are invincible and OP, but other people aren’t.

    Where the weight of impossible decisions pulls you down into the depths of despair.

    I think the tech is finally getting to a point where it’d be possible to fill a virtual city with people powered by AI that makes you really care about the individuals in the world. To form relationships and friendships that matter to you. For there to be dynamic characters that put a smile on your face when you see them in your world.

    And then to watch many of them die as a result of your failures, as despite being an invincible god among men you can’t beat the impossible.

    I really think the gameplay in a Superman game done right can be one of the darkest and most brutal games ever done, with dramatic tension just not typically seen in video games. The juxtaposition of having God mode turned on the entire game but it not mattering to your goals and motivations because it isn’t on for the NPCs would be unlike anything I’ve seen to date.