This seems neat.
Better title would be “Genetic algorithm learns how to make functional Factorio blueprints”
I agree. I was around for machine learning back in 2015, but now I see the word AI and I start getting weird feelings about it.
Ok
Gen 1 is so much cuter of a Factorio though. Hit the fuck Go Back button.
But I want to play factorio, not have an AI automate it for me
I mean, nothing is stopping you?
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.
No generative AI is used in this video
It’s generating Factorio blueprints with machine learning, that is “generative AI” by definition
“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.
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?
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.
Ok, so what you’re saying is it’s about whether the goal can be precisely defined.
Afaik the basic way they are trained is conceptually very similar or the same as genetic algorithms: GANs are similar to mimicry in evolutionary biology, with an evolutionary arms race between both networks.
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).
Not the modern colloquial meaning of “generative AI”
Just because someone is a cunt doesn’t mean they are a Scotsman
