It is weird and almost alien how AI designs factories. When Claude announced Fable 5 they also did a Factorio demo that was the same kind of designs and a lot of hand feeding and direct insertion. In some sense it proves to me that llms are not just copying and are actually creating a bespoke solution. But I honestly expected more from frontier models
To them the player character is just as good as a belt for transporting materials.
The player character actually does have an extremely high capacity so if you are constantly running between chests your factory will still be reasonably high throughput.
What are you talking about? Maybe at the beginning, yes. Everyone carries stuff around when you have 2 assemblers, but once you start building your bus, the throughput of the player is orders of magnitude worse than using belts (or, if you're into that, bots)
For the purposes of launching a rocket the player character's inventory is vast.
> In some sense it proves to me that llms are not just copying and are actually creating a bespoke solution.
Is the weirdness of the designs meaningfully beneficial in any way that the AI has figured out, or could it for example be that the training data the LLMs learned from are too different from the type of data it would need to learn from in order to interface properly and play the game better? And then because of that incompleteness, the LLM has to hallucinate a lot and it results in weird outcomes.
No their weird designs are not better in any way - yet.
I think one of the problems is that AI has no sense of laziness or time. Unless it's in their training data or prompted they're not going to bother automating something
Actually if you estimate the time required it's plausible that player feeding comes out on top, especially if setting up automation is not that obvious. But human player would never play that way, they would get bored from the repetitiveness, and the micro scheduling would be a headache. So the game designers never really have to close that gameplay loophole (or closing it would make human experience worse).
I have a similar problem on my GK2 vibegamed playthrough (see https://news.ycombinator.com/item?id=50302771), if I want computer to play similar to how a human would, I need to artificially close that loophole (for example, AI prefers to gather/eat low-tier food to cooking better).
Anyone making this claim just hasn't played a lot of factorio, because this just isn't true. Player feeding is fast in the early game, but it just doesn't scale. There's too many buildings to feed and it takes too long to walk between them. People have already made tool assisted speedruns, and as expected it involves building a huge automated factory as quickly as possible.
I played Factorio quite a bit..
I said it's plausible. Perhaps not for basic materials, but things like robot frames, higher tier research packs, modules, anything that has low component amount compared to time or amount required for crafting.
Even speedrunners do quite a bit of handfeed. And if AI/player cannot figure out the automation fast enough - the handfeed might easily come on top.
This is where human-directed looping revision fits in on a lot of my projects.