No, in the game you can push the words around and redefine the effects that each object has. So you can push the word rock and make it say "rock is win" and touch the rock to win
This is actually interesting, because I remember sokoban being one of those games that are hard for a computer to find a winning solution for, while being quite easy for a human. So they made their own game inspired by sokoban with very simple levels?
LOL. Lmao, even. Like the first five levels of Baba Is You are simple. Past that, that game is a mf menace. Most sokoban games won't give you the opportunity to accidentally zero-sum yourself out of existence or turn every wall tile into a walking controllable copy of the player. BIY requires some extremely out of the box thinking sometimes.
that would require an LLM then, but also multiple full walkthroughs are explained in text on the internet, so how would you be sure it was figuring stuff out by itself?
As I said: I don't think an LLM could do it (since LLMs can't reason). Just saying that it wouldn't have to deduce the mechanics from a single screenshot.
Look up reinforcement learning, it's the branch or ML/AI that Alphazero was based on. Video games are actually a main focus area for that kind of research.
Haven't played the game but I'm guessing based on the little I've seen:
push rock into water
cross rock into room
swap "push" for "win"
touch rock and win?
I have played the game (baba is you) and that is the solution.
How do you cross while rock is push?
Can rocks go through walls or is "stop" for more than baba? Otherwise break water is sink with the rocks.
Also, do we know if this even has a solution or is just a shitpost?
Water is sink, so rock and water will destroy each other. Think of the rock as if it is as tall as the water is deep, and creates a platform.
Ah fair
Wouldn’t you need three rocks though?
No, in the game you can push the words around and redefine the effects that each object has. So you can push the word rock and make it say "rock is win" and touch the rock to win
Oh interesting. Maybe I check this game out.
You absolutely should, I had a blast with it. It's truly a masterful puzzle game.
It's way easier to play than it is to explain solutions in text, for sure.. also it's friggin great
No you can also move the words "push" and "win", so you can swap them making "rock is win", you can then touch the rock to win the level
According to the comment that claims it has the solution the instructions rock is push is rock, you can push it until rock is win
Also Baba can stop being You in some puzzles to. That game is great
accidentally been walls too many times... been ages though.
"Water is sink" will make the water and the rock disappear when they collide.
Still easier than half the captchas I see these days
I suffered through Baba Is You and gave up around world 6.
(Suffer in a good way)
This is actually interesting, because I remember sokoban being one of those games that are hard for a computer to find a winning solution for, while being quite easy for a human. So they made their own game inspired by sokoban with very simple levels?
This game is Baba is You. A great puzzle game that gets pretty difficult as the game proceeds
LOL. Lmao, even. Like the first five levels of Baba Is You are simple. Past that, that game is a mf menace. Most sokoban games won't give you the opportunity to accidentally zero-sum yourself out of existence or turn every wall tile into a walking controllable copy of the player. BIY requires some extremely out of the box thinking sometimes.
I'm curious if you could give an image like this to an AI that supports image recognition like ChatGPT-4 and ask it to solve it for you.
This is actually a really interesting question. A modern LLM probably couldn't do it, but I wonder if something like Alphazero could?
My guess is that no current AI is capable, as it requires abstract reasoning and precise movement. But maybe in the next 5 years.
from the image alone, no, because there's no way to intuit the mechanics of anything
I don't think that an LLM could do it. But the mechanics of baba is you should be in the training set, since it's a relatively well knoun indie game.
I feel like the amount of data required to train any neural network would be larger than all the levels that currently exist for baba is you
you'd probably just end up overfitting the hell out of your model
But the mechanics are explained in text on the internet.
that would require an LLM then, but also multiple full walkthroughs are explained in text on the internet, so how would you be sure it was figuring stuff out by itself?
As I said: I don't think an LLM could do it (since LLMs can't reason). Just saying that it wouldn't have to deduce the mechanics from a single screenshot.
Look up reinforcement learning, it's the branch or ML/AI that Alphazero was based on. Video games are actually a main focus area for that kind of research.
As for beating Baba is You, I'm not sure. OpenAI did make an AI that could beat people in Dota - https://openai.com/research/openai-five/
BRAIN IS HURT
SDDDSSAAWASSSSSSSDDWWWDSSSAAAWWWWWWWWDD