• 2 Posts
  • 318 Comments
Joined 3 years ago
cake
Cake day: June 3rd, 2023

help-circle






  • Isn’t that the opposite of what we’re “seeing” now with the expanding universe and dark matter (not anti matter) being the reason for space to grow?

    Anti matter and matter live inside the space, that dark matter is “producing”

    At least that’s my layman interpretation of looking at some videos and reading some stuff

    So, I have no clue ;⁠-⁠)





  • Sadly, that’s true

    Tried to refactor a spaghetti code state machine and thought, well, AI should handle this well. All the logic is there, just separate it into small functions to clean up the large one.

    None was able to, alone because of the context window already

    To be fair though, I tried Mistral online and it also stumbled around. ChatGPT was a complete clusterfuck - haven’t tried Claude.

    To be even fairer… it’s a really large state machine, which was written on site during a fever and in stress - so… To defend myself a bit as well, how it even came to that ;⁠-⁠)

    But seems, I’ll need to go through this myself
    Actually thought, that this would be a perfect example for using AI…




  • Arch is great in my opinion

    I’m not sure, if it was just my young age/experience with Debian, but now with Arch I could always save a system. With apt I sometimes preferred a complete re-install.

    I actually really like Arch(& Arch based systems).

    If that is the public opinion with C++ and Arch, I’ll need to re-evaluate my masochistic tendencies, it seems



  • And I fucking love it

    I hate java with a passion, C# was fun (but at that time only available through the .Net nightmare) and I grew up with (Turbo ;⁠-⁠)) Pascal and C

    So, I’m feeling rather comfortable and at home with C++

    I’d like to do a bigger project in Rust once at least, but with my current project already the compile times are between 20/25 to 45mins (depends, if you have the build server available or if you need to make up with the IPC).
    so, I guess, those iterations would become even longer with Rust

    But I’m also having the advantage, that my applications are running very, very isolated. So I don’t really need to take care about exposure and attacks.

    Still… Finding a memory leak or some shared memory fuck up is everything but fun…

    Especially as most of the logic runs in kernel space and debugging possibilities are mostly reduced to traces/log files

    Still, I love it
    Maybe it’s because of the thrill ;⁠-⁠)





  • I’m not sure, if I understand the environment completely

    Those agents were the virtual incarnations of the AI in the sim city and the respective government - correct?
    And the AI needed to take care, that those agents didn’t died, like of hunger or what?
    That’s not really what those LLMs are trained for.

    Not sure, what they expected

    Currently searching the article for the original source, maybe this gives more insight

    Edit: ah, just in the first paragraphs it is
    https://www.emergence.ai/blog/emergence-world-a-laboratory-for-evaluating-long-horizon-agent-autonomy
    Completely missed it on the first read.
    Let’s see if this makes more sense…

    Edit 2: ok, if I get this right, those agents really were specific virtual individuals
    Not sure what they expected. First, LLMs are not really build to “live” as an individual as they aren’t real intelligence and can only role play individuals based on their training data.
    Second, why should they be super moral or “better”?
    Again, they just role play depending on their training data and built-in prompt bias (not sure what the prompt injection of the company is called)

    If you train an AI on governing such a world, it probably start gaming the system, depending on what values are important to “win”
    As we have already seen with machine learning in the last decade(s?)

    Funny experiment nevertheless, but not really useful in my eyes - and I’m everything but a defender of the current use of LLMs