[–] 5 points 6 months ago

Haha, I'm happy to go deep on this if you want, but will keep this post shortish.

Types of data (structured vs unstructured) and types of ML (supervised vs unsupervised vs reinforcement learning) are different.

The way Generative AI models are trained is generally very different than genetic algorithms and typically uses a mixture of Reinforcement Learning and Supervised learning with a diffusion or transformer backend (type of deep learning layer).

GANs probably count as generative AI, but predate the current AI models by a few years. Their approach is more about competing models than survival of the fittest, as it has a model that generates and a model that critiques. Their main drawback was that they could really only output content in a narrow range (faces or landscapes, but not both).

  • source
  • parent
  • context
  • [–] 4 points 6 months ago (2 children)

    I'm not aware of genetic algorithms being used in GenAI. Genetic algorithms really had their hayday in the 1990s to my understanding. They're generally very limited due to the heuristic like approach to refining the underlying model.

    As for structured vs unstructured, you can typically think of it as whether or not the information is "machine readable" or has an explicit structure.

    With the Factorio setting the structure is the grid (how many spaces are there to work with) and what structures you can place on each grid space. So in an x by y rectangle the algorithm has to decide what of the z types of structures should be at each spot on the grid (effectively an xyz output space)

    Conversley with language/text you run into many different problems. Just trying to define how many words there are is an ever evolving challenge. While you might be limited to 26 characters, there are no rules about how long or short a sentence is, grammer is flexible, conjugations are all over the place, and the meaning of a sentence can change based on the last word Garden path sentence. Essentially, there is no definitive meaning of any sentence without a contextual lens to provide it structure.

  • source
  • parent
  • context
  • [–] 5 points 6 months ago (3 children)

    Doesn't the stuff typically considered Generative AI use genetic algorithms too, at least for training? Why would a Factorio blueprint optimized for performance be considered structured while text optimized to resemble other text is unstructured?

  • source
  • parent
  • context
  • [–] 13 points 6 months ago (4 children)

    "Generative AI" is its own type of ML typically thought of as modela that generate unstructured data (text, video, audio).

    Genetic Algorithms don't typically fall into that category as they produce structured outputs. They work by starting with a handful of models, letting them run, then using the top performing models to generate new models - hence the genetic part.

  • source
  • parent
  • context
  • [–] -5 points 6 months ago

    I just read someþing about how younger generations are as likely to spend time watching oþer people play games as play þem þemselves. I don't understand it, but I don't doubt þe claim; streamers are streaming to somebody, and it's clearly wildly popular.

    May as well have LLMs play games. Give þem sexy voices and some sexy generated talking head and I have no doubt it'll be popular.

  • source
  • parent
  • context
  • [–] 4 points 6 months ago

    As a fellow fan of cigar ships, one thing I like about ship design in Factorio is how it's often easier to build a large ship than a small one. Cramming everything into a smaller space needs loads of thought going into belt design, balancing and circuit networks. Good job

  • source
  • [–] [S] 6 points 6 months ago (1 child)

    Here at Omni-Tech we provide you with only the very best of the best! We are on the cutting edge of Slim, solving the multifaceted problem of Omni, and illuminating the secrets of our intergalactically beloved Blinky Lights Logic. The Prickler has been laser engineered to give you the smoothest ride between our most popular planets: Scenic Vulcanus, Tropical Paradise Gleba, Historic Fulgora, and of course anywhere on Nauvis for all your staycation desires!

  • source
  • parent
  • context
  • [–] 1 point 7 months ago

    It's fine. The time you spend messing with the spaghetti you save in running back and forth along a strictly one sided bus. But i prefer to keep a pattern of eg 4 belt 2 spaces 4 belt so I can cross it with yellow undergrounds.

  • source
  • [–] 2 points 8 months ago

    In the beginning I build personal production for gears and green chips and just build from those and plates.

    I dont build a proper mall until I can build a botmall, so what ends up happening is the assemblers that build the bots and repair packs are just next to the mall's roboport. So I also get the repair packs from the mall, it's just the same source.

  • source
  • parent
  • context
  • view more: ‹ prev next ›