GPT-5.6 Sol can beat Factorio on peaceful mode

Hah I dunno, I think most human players wouldn't find that very fun and would instead take that as an opportunity to refactor the factory for optimized performance (i.e. the core gameplay loop)

youre not really sure how to set up some of the logistics/how much of what you will need where ahead of time

Like I want to see what Pokemon strategies it uses: Does it try to brute force with its starter? Does it try to load all of its HMs onto one or two Pokemon? Does it use Flash? If it needs to catch a new Pokemon to beat a gym leader, how much does it remember about which species it encountered where and what their levels were?

It's fun if you have a handful of people playing, but it would quickly go towards negative reviews if you tried to sell it.

Not useful enough that I actually play with it, but it was capable enough to be useful even just with sonnet.

I think there's a bit of a lack of knowledge of game history on both sides, because we already know it can be fun when a game is designed around it. It worked in Façade (2005!) and it worked in Starship Titanic (1998!!), and both of those could have worked even better with the technology we have today.

One type of game that seems like an obvious one to me, is something a bit like The Sims except that the characters' decisions and speech are LLM-controlled. Maybe one of the characters is player-controlled, so you can interact and talk with everyone else. Or to describe it from the other direction, it'd be a kind of interactive fiction like AI Dungeon invented, but grounded in a physically simulated setting.

(Not sure how prohibitive it would be to do anything interesting with local LLMs of any kind in a big game, given how many platforms/setups you have to make the stuff run smoothly on, and the sheer amount of RAM they would bind)

These old basic algorithms often have mathematical proofs that they will converge to optimal behavior, and they do so fairly quickly. Turning the complex world of the game into a Q-table would require some creativity and judgement, but is not that hard I think.

In the end we would have a controllable AI that actually does adapt. That's my hope anyway.

same with the df artworks. get kitfox to design some art styles for dwarves, elves, goblins, and humans, and then instead of just reading

"this is a fine engraving of a dwarf. it concerns the events of 102 when ulrist fastbuttons was elected mayor. ulrist fastbuttons is sobbing"

both American and Chinese labs aim their models at coding and knowledge work, so they penalize adult themes in post-training.

A little unpolished because it was bolted on by fans and not the original game developers, but otherwise very impressive.

This has been true for every model since 2023. It's not nearly as big of a factor as people believe it is

The models these days have 3 components that is for sure going to get better and better

1. Very good vision (it can identify almost anything in a picture) 2. Keyboard and mouse actions (slow but it does it well) 3. General world understanding (this one is toss up but given Astra or Fable, it surely does well even if it takes a while)

Now combine all these with specific RL environments that may use specific games which also generalizes to an extent and we have a system that can only get significantly better from here.

As for speed, I’d say it’s a question of how much money you are willing to throw (like Cerebras for example).

There are full blueprints for factories online available to copy-paste in its training data [1]

I wouldn't be surprised if you can beat the game by just copying a bunch of blueprints from the web and chaining them together.

This is an old game relatively speaking and its been optimized to hell.

0: https://factoriolab.github.io/2.1

1: https://factorioprints.com

Part of the reason players try to automate manual feeding is the annoyance factor, which AI doesn't care about.

I’ve yet to see running these LLMs on Ultra-fast (8x speed on Sol). Wondering if that’s fast enough to do real time

So they get into a cycle of: 1. Get attacked 2. Build a few turrets 3. Get attacked. They don't consider buffing up their defenses or going out to deal with the threats or preemptively placing turrets when they expand. Not without human probing.

Also, they had the same issue with hand carrying resources around as some other comments here mentioned Sol did.

[1]: https://factorio.nickwinter.net/

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.

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.

Why even play the game?

Boring though without something to attack you imo