Topic.
Context: Every few months I go back to Blue Prince. It isn’t a big game, so I haven’t uninstalled it from my Xbox. I app bought it on Steam, to play on my Mac, but it plays better on Xbox, so that’s where I play.
Minor spoilers in the next paragraph.
I’ve never gotten to Room 46. I’ve gotten to the Antechamber. I’ve been underground, I basically understand how to beat the game. I also understand that Room 46 just beats the tutorial; there’s way more game past it. I have three of the letters. I have the grove unlocked, the outside shed the garage unlocks, and I have the gem cave. I figured out the puzzle of the two drawings in each room. I know what that message is.
Still, I’ve only failed and I think I have around 50 runs?
I’ve asked Google and apparently nobody’s tried this? I keep seeing a YouTube video with the (bait?) title that it’s not RNG.
I haven’t tried this, but I keep thinking, if I ask a chatbot to play the game, it tells me which way to go, I tell it the three choices, it tells me which to pick and where to go, I think that would work. But is the chatbot guaranteed to win? If not, can the game generate runs that simply can’t be won? Or is there enough RNG that both can be false?
I get that a lot of people don’t like AI. That’s why I checked to see if it had been done first. If anyone had done it or tried it, I couldn’t find it. I’m really more interested if it can or can’t, or if one can’t but another can, than actually doing it. Most games can’t be played by having a chatbot walk you through it. Those that can — point and click adventures — can similarly be beaten by simply following written directions. They don’t have RNG. Something like Life is Strange, for example. You can get all the collectibles, and achieve the optimal outcome, just by following a guide. But, Blue Prince is built differently.
You must log in or register to comment.
Could a bot (Not LLM) be made to beat it? Sure. It wouldn’t be beating the game’s RNG any better than a good Blue Prince player though. Bots following decision trees based on probabilities is nothing new.
If you’re going to take out the joy of doing the puzzles yourself, you may as well watch a streamer play it. I’d recommend LordMinion777’s play through, he really enjoys the game for what it is.
If you’re only touching the game every few months it’s not a surprise you haven’t gotten to Room 46 yet. You remember the basics everytime you go in, but you have to relearn the patterns and interactions so you’re just putting yourself in a failure loop.
lil indigestion also has a very comprehensive playthrough.
Yes, if I just wanted to see the ending, that is exactly what I would do.
I remember more than the basics, but, good point.
Sometimes I feel like I’m not smart enough for Blue Prince. That’s fine. Puzzles made by smart or smarter people can stump me. That doesn’t bother me, and I still love the game for what it is.
LLMs do not have a world model. They are what is called “theory free inference”. Due to this, they can’t actually even play chess. There is no actual awareness of context (which is part of the linguistic trickery around its features, see also “hallucinations”). It can, however, provide answers to questions about the level, even though its answers will be based on probability occurrence and not correctness or understanding.
Humans do not have a world model. They are what is called “animals”. Due to this, they can’t actually even play chess…
The only way an LLM would Beat the game is if it’s trained on it over and over and over so it’d understand the principal and strategy. However, LLMs aren’t built for that, for that you’d be a statistical or probability model AI.
LLMs aren’t built for that, for that you’d be a statistical or probability model AI.
Pretty much all current gen LLMs have that capability. They’ve gone a long way past being just language models.
I figured if it could parse a wiki and all that’s been said about the game, that it might be able to forge a winning path.
Look, I know the go-to lately for a lot of people is “just ask ai”.
My problem with that, is, it’s like cheating on a test. Taking the easy route. Without the critical thinking skills, without the development of figuring out how things work, we’ll lose the ability to think differently!
What’s the danger or risk with that? We become more docile, controllable, herded like cattle or sheep. Taken advantage of by the ultra wealthy because we give up our ability to think and act differently.
There have been multiple studies of this being done that show this is the way we’re going. I also don’t use AI because of the ethical issues behind the technical inefficiencies (very power hungry, race for “best”) and skip the “should we be doing this on the first place”.
I get that. There’s a whole debate worth having around AI in general, and there are comms dedicated to it. Even people spamming their point of view in every other comm hoping to change minds…
I’m just wondering if it can without trying to touch if we should. There are smarter people than me debating that in other places. While preaching to me might feel like an easy win, it won’t really address the problem, and I won’t not seek an answer.
I don’t like AI because it’s an inefficient use of resources, but AI used to make something that people benefit from changes the equation, though it’s subjective how much it needs to change it to matter.
https://www.youtube.com/watch?v=Fa5el2uhP_8&t=92 LLMs can play Portal. So Blue Prince maybe could be done the same way. It is harder than Portal though.
“Plays”. Only a few minutes into the part 1 video it preempts the tutorial jump instruction. Before any indication of the upcoming jump instruction it both shows knowledge of it in the reasoning and actually jumps.
Maybe because Portal 2 is an old game probably well described in the training data. Might be interesting to see how well it works on a new game.
