You gotta admire how versatile and full of possibilities Minecraft is. The game has been out for about 15 years, and people are still doing unique and interesting things with it.
With the exception of not supporting multithreading, Minecraft is almost a perfect environment for so many things. Just simple enough to not make everything a daunting task, but just complicated enough that there are many different angles to experiment with or ways to add things yourself.
The only other game with as much lasting prevalence imo is tf2 since even now every single meme and event or situation gets turned into a tf2 parody video with millions of views in 2024 still
It's kind of cute how the AIs always place some "special" block as the top of their pyramids instead of just making the whole thing out of one material
@@zyansheeptrue, the rich in Egypt I believe had gold blocks at the tip of their pyramid, a specific guy who was important for some reason I don't remember, probably was a pharaoh- wanted a solid gold pyramid but because that's unreasonable he eventually settled for a gold cap for the pyramid.
@@Nezha_Main That's right, one of my favorite things about the pyramids is that when they were built they didn't look like just rough stacks of sandstone, they were smooth and shiny white because of the decorative layer of limestone on the outside, and the gold cap on top just added to the image. Over time these materials were reused or stolen and all that was left was what we see now. Anyone interested should definitely look up some images of what we think they look like at the time
@@PinkeySuavo The tinted shadow on the ground with his shader pack is creating the geometric gradient pattern because the sun was at the exact angle parallel to the layered glass sphere the AI built, which is diagonal both laterally and longitudinally.
The AI doesn’t even know what that tower looks like IRL, you should get it to describe its own design first so it realises what it’s even building. I’d also recommend something like snippets or get it to make its own codeable rulesets to building before it builds.
Absolutely, I really feel like a secondary model layer whose job is to describe what the building might look like if it was built in minecraft(block types, specific geometric patterns, etc) could go a long way here.
this is a great suggestion! personally i usually use a multi-step process for my tasks that involve AI as well, rather than trying to get them to solve it for me all at once. break the problem down into many separate chunks, go through them one by one to get some solid foundational blocks before combining all the results into a coherent set of solutions. such is the way of programming.
yeah, like if it had a command that took a 2d array of blocks and rotated it around an axis, that would allow it to make a coliseum by drawing a cross section.
I’m really curious to see where AI inside of minecraft goes. I imagine in a few years we’ll have a way to train them on good and bad builds, give them a better concept of what constitutes a “building”, but what I’d REALLY love to see is some kind of simulation between them of an SMP, giving them access to baritone and allowing them to work out how to get things done in an open environment. Let their decision making guide them to the best path. Have them identify problems and come up with contextual solutions. E.G. I’ve been attacked by monsters outside my home at night, the best course of action would be to light up the surrounding area and build a wall to keep monsters out. Have them break that down into simply steps that don’t have to be ai powered but can just be automatic, craft torches, go strip mining to get resources for the wall, etc. I saw a paper about a similar project a while ago where they put down LLM agents in a simulated town and the “people” in the town had a small memory where they remembered previous experiences and had some agency on what they wanted to do, one of them planned a Valentine’s Day party and invited guests to it entirely on its own with no input. Very interesting stuff.
The paper you're referring to was done to advance research in multi-agent cooperative llm systems but a better examples of this would be the "Voyager" minecraft-llm paper. I've just completed a masters in this area, and i'll say we could do this today, it's just it would be costly to train and we have better ways to use our resources than advancing minecraft ai. When making a minecraft AI for research purposes Minecraft is used only as a proxy for the real world, with the idea that if we can make a solution that is super general and solves minecraft it will solve real world useful tasks. If we start coding minecraft-specific tasks for it to do, we're distracting ourselves from the proxy and just making something to play minecraft.
as I've been watching this series I've been thinking about how cool it would be to have a mod that adds a ton of alien-like AI generated structures, it really feels like aliens looked at human architecture and tried to re-create it. I can just imagine stumbling upon those pillars at 4:35 and following them all the way just to find an empty, strange looking building with seemingly no purpose. gameplay wise I imagine players would be disappointed but personally I'm just here for the vibes, and the vibes these buildings give off are immaculate.
I avoided using this word in my original comment because it gets a bad rep, but the whole vibe is very "liminal", it just feels like you're not supposed to be there almost. Everything feels unfinished, and unnatural. The pyramids were pretty good but the smaller structures like the colosseums really give off the vibes I'm talking about.
This might happen actually i hope a modder do it, i would also like to have a AI npcs in the world, imagine wandering finding a npc and try to talk to him to either help u or do something for u, and imagine if they have random personalities, like some of them are agressive, some are not, some are lonely and act weird, i feel it would be insane
There’s something really amazing and unique the even “incomplete” buildings are. Very symmetrically interesting patterns! Keep on making more of these tests and videos!
@@EmergentGardenI could see pros and cons of this. The reduction of the chat spam seems nice, but in the event that it starts placing blocks somewhere it shouldn’t (like what happened in this video), it might help to see the coordinates aren’t right and easily find where it was. It’s really just up to you which you prefer.
Uhhh maybe also sendcommandfeedback bc like that's for command blocks. I don't think they use command blocks (also ik there is probably something else there but I use bedrock)
I love videos like this that just explore what AI can currently do and treat it as a novelty to play with, rather than making any grandiose promises or predictions. The societal implications of this tech are huge of course, but we can also just slow down, take it in, and play some video games.
11:08 lmao. When I was 9 in 2011 I got operator to a small server that had world edit. So I wanted to build a huge hollow glass sphere in the sky... but I set it wrong and the server crashed. When I re-logged, parts of the world for hundreds of blocks were made of glass shapes that weren't quite fully rendered into the giant sphere I had tried to create.
Are the models integrated with vision, or is it literally just "blindly write code and hope for the best" ? I know it'll be expensive, but imagine if you supplied the model with periodic screenshots.
It has vision but not in way we have. It basically has coordinates of blocks nearby not like it can actually see anything it created. All of these things are just numbers to them
@@braineaterzombie3981 I'm just saying, most of these models (not sure about Llama, but it's open source so I'm sure people have made Llama Vision or whatever) have vision capabilities. As in, you can send them pics and they'll understand. Not EXACTLY the same as how we humans 'understand' images, but good enough for use.
@@braineaterzombie3981they do have vision, like in "image data input". 4o even also has audio input (and output even). Passing stream of images still hasn't been released yet, but it's possible with 4o For now we can pass occasional screenshots to gpt4o, gpt4vision and Gemini 1.5
This is a much bigger deal than the narrow domain of minecraft. You’re showing how we can augment the capabilities of the models with better design choices for how they navigate their task. This is a multiplier on algorithmic / scaling improvements for future models.
I wonder if it would help to use a multimodal model and automatically take screenshots of the building for feedback so the model can iterate until it judges it to look good.
These kinda remind me of the feeling of the original backrooms with these structures that are almost human but are very clearly not human at the same time
I believe for the /setblock command you can use keep and it'll only change the block if it's an empty air block - then, if something goes wrong while the bots are building, you could tell them to just replace everything they just built with air as a sort of "undo" feature
I like that some of these look a little alien, that one listing pyramid with all the gaps feels so strange. That Parthenon, colosseum, all have a strange, nearly otherworldly aesthetic, vaguely recognizable but still strange. I like it.
Your content is awesome. i love these lil guys doing stuff in minecraft but i want to see like tutorials at first 2 minutes of the next video about how to set up!
Cool video! I remember once having an idea, it would be cool if there was a server where only AI players would play, who would self-learn thanks to live players, after which it would be difficult to distinguish them from real people, they could communicate with each other, build houses and grief each other
I'm fascinated with all your work. A very different but understandable way to show the comparative potential of the various models. And one can only imagine how videogames are going to look like in 3 years time. We are truly at the doorstep of a new Era.
The Parthenon* the AI built has a great vibe. An Abstract psuedo roman structure, and broken up columns floating in neat rows away from it in a flat plane. I can see something like this being used in a story about something otherworldly. Precursors, an AI ran cyberspace being broken, a depiction of heaven, etc. Accidental AI art.
Imagine the possibilities. An interesting idea would be to see how he can change the world, ask him to delete everything and create something else to see his capabilities... it would be incredible
You could use a greedy-meshing-like approach (but with volumes instead of faces) to post-process the AI's output into chunks of the same block type. Then you can use fill commands to place multiple blocks at once, which would make it much faster. Btw I believe you can also disable chat messages for commands, so the chat is not spammed with setblock messages.
Damn, that's a huge improvement 🤩🤯I hope more people will see this channel 😊If in the future we can get the models to understand us more carefully and take longer to write the proper code, it'll be awesome. Right now, every AI from every field is trying to make stuff as fast as possible, so they make a lot of mistakes and we have to iterate multiple times 😅I wish they would just take their time and do it nice, i don't care if i have to wait 2 min instead of 10 sec.
A while ago I tried to get this working, but they were blissfully unaware of their code not working, or that they had previously written code. I might be able to get it working now, but I"m 100% demotivated. I'll just watch your videos instead. Also, you thought about experimenting with instructing the agents to build a fully functional vanilla neural network?
If anyone sees this, I need an explanation. I still don’t rly understand how the AI is kinda just building in Minecraft. It’s just a language model. Is it just coding and that code is put into “mindcraft” then it translates that code into the characters doing something? And how does it kinda just automatically build something? I don’t get how AI is using cheats. And how is the code that AI is creating to build different from mojang’s code that is used to create terrain and villages and stuff?
"Is it just coding and that code is put into “mindcraft” then it translates that code into the characters doing something?" Basically, yes. They write code that gets executed in the game, "mindcraft" being a framework to facilitate that. "And how does it kinda just automatically build something? I don’t get how AI is using cheats." The agents build internal representations of the world, use those to plan buildings, and write code to implement the plans. That's an oversimplification, but yeah. The cheats are just code in the games codebase, and are called from the command line like other functions. They need to be enabled by setting allow cheats to true, IIRC. "And how is the code that AI is creating to build different from mojang’s code that is used to create terrain and villages and stuff?" The agents build only what they're told to, but they can create new designs. The game code has static designs for everything. These are all just my observations.
I think i understand why Llamas skyscraper was so short. It is ten blocks (floors) tall so theorethically it did the assigned task right, it just so happened that what the AI considered a floor and what you considered a floor differed. It just thought that floors don't also need some hollow space in between them.
I'd love to see them try something with commands/command blocks, like "hey gemini, drop me a pair of unbreaking 2 boots that also apply a haste affect". Could be useful for SMP servers
I am currently doing a similar thing with AI. I am writing a python script to nearly mimic the functionality of chatGPT, with my own added features such as file creation, txt file reading, and internet searching. I also created a makeshift memory for it, that allows it to recall past conversations even if you restart your computer or the model. All of this runs locally. The issue im running into is having it write commands to execute these different functions.
I just saw the last video, and wow! What an improvement! Is this possible with WorldEdit commands? Originally, that's what I assumed the 'cheats' were. Watching the build step-by-step with setblock is really cool to watch, though. The super large circles with almost zero error, and the large glass spheres especially were impressive. Pushing the forefront of minecraft technology.
I still see a huge gap with AI; it cannot SEE what it is building as it's making it. there isn't even a workaround (that I can think of) for this, which means that they will continuously be unable to notice and fix their own bugs in their code
If you watched one of the previous videos, Claude realized it made a mistake in the middle of building and tried to correct it, only it ended up building the second house into the first house
You could possibly write code manually to check if the block being placed is more then a certain distance away from the bot to prevent accidental griefs, maybe make horizontal and vertical different values though in cases like its tower
This is really cool, we can't lie about that. Have you discovered anything new with the AI's since this video? When is your next one? I'm really enjoying your videos, your showcasing of their abilities are fun to watch.
This is one of my favorite AI projects to follow, particularly because of the rapid advancement of AI and the growing competition in the LLM market. Comparing the capabilities of different AI agents in Minecraft is such a novel and awesome idea, like something straight out of the Matrix. Just imagine how advanced these bots would be if they utilized Multimodal models such as GPT-4o!
I hope that one day when computers are powerful enough someone would create a mod that incorporates one off ai generated buildings into minecraft survival gameplay, it would make minecraft feel more mysterious and fun kinda like the feeling we get back when we just started playing minecraft without knowing much about gameplay mechanics
It'd be cool to see them try and build something in survival start to finish. With LLMs as the glue between the cracks of Mineflayer, I'd be curious to see if, given a schematic or something, the bots were able to find and craft resources to create them
Something that would be interesting is seeing how the models fare in making redstone projects & logic. I doubt they would see much success seeing as they struggle with pyramids but it'd be fun to watch if nothing else
"Don't worry I'm not gonna crash into them" 💀💀
Dark!!
👨✈️✈️🏬🏬
This dudes humor is something else
@@BadChess56It's so subtle, but when you hear it, it hits different
mr president, a second minecrafter has hit the towers
You gotta admire how versatile and full of possibilities Minecraft is. The game has been out for about 15 years, and people are still doing unique and interesting things with it.
With the exception of not supporting multithreading, Minecraft is almost a perfect environment for so many things. Just simple enough to not make everything a daunting task, but just complicated enough that there are many different angles to experiment with or ways to add things yourself.
@@Gandhi_Physique As long as you have enough runtime to deal with it being one of the worst optimised games I've ever played
The only other game with as much lasting prevalence imo is tf2 since even now every single meme and event or situation gets turned into a tf2 parody video with millions of views in 2024 still
It's kind of cute how the AIs always place some "special" block as the top of their pyramids instead of just making the whole thing out of one material
Sentient love to build tall
He tells bots to do this to check their capabilities
Humans do this too!
@@zyansheeptrue, the rich in Egypt I believe had gold blocks at the tip of their pyramid, a specific guy who was important for some reason I don't remember, probably was a pharaoh- wanted a solid gold pyramid but because that's unreasonable he eventually settled for a gold cap for the pyramid.
@@Nezha_Main That's right, one of my favorite things about the pyramids is that when they were built they didn't look like just rough stacks of sandstone, they were smooth and shiny white because of the decorative layer of limestone on the outside, and the gold cap on top just added to the image. Over time these materials were reused or stolen and all that was left was what we see now. Anyone interested should definitely look up some images of what we think they look like at the time
That tower joke caught me off guard 💀💀
ikr
same
"See those towers over there? Let's fly towards them"
"Don't worry I'm not going to crash into them" was so out of pocket
me when september
:)))))))))))))))))))))))))))))))))))))))
@@solarisNT-v4j eleventh
Some unlicensed 13 years ago
6:05 The sun being at the exact parallel angle making the geometric shadow was a fantastic coincidence
Also, you should install the Distant Horizons mod so we can see all the builds in the world at once!
If you are on Nvidia, Nvidium does an even better job than distant horizons!
what do you mean?
@@PinkeySuavo The tinted shadow on the ground with his shader pack is creating the geometric gradient pattern because the sun was at the exact angle parallel to the layered glass sphere the AI built, which is diagonal both laterally and longitudinally.
@@michaelproeber1953 wouldn't the effect be the same even if sun was higher/lower etc? It looks like a normal shadow to me :P
0:18 I’ll give that joke a 9 out of 11
Underrated comment
9:17 that would be sick having a ancient city inside of a pyramid
The AI doesn’t even know what that tower looks like IRL, you should get it to describe its own design first so it realises what it’s even building.
I’d also recommend something like snippets or get it to make its own codeable rulesets to building before it builds.
Absolutely, I really feel like a secondary model layer whose job is to describe what the building might look like if it was built in minecraft(block types, specific geometric patterns, etc) could go a long way here.
this is a great suggestion!
personally i usually use a multi-step process for my tasks that involve AI as well, rather than trying to get them to solve it for me all at once. break the problem down into many separate chunks, go through them one by one to get some solid foundational blocks before combining all the results into a coherent set of solutions. such is the way of programming.
yeah, like if it had a command that took a 2d array of blocks and rotated it around an axis, that would allow it to make a coliseum by drawing a cross section.
the best pyramid turning out to be surrounding previous failed pyramids feels like a metaphor for something, but i'm not sure what.
Every failure is a crucial step towards progress
it's almost liek sum king of... forshadow wing...
Wise word to remember about A.I. "The more creative powers you give them, the more destructive powers you give them. There is no way around it."
tbh if humanity can't find a way to coexist with or survive against something we created ourselves that's just a massive skill issue on our end
yeah that quote stuck out to me as well... it goes hard tbh
Killswitches??
Real
I’m really curious to see where AI inside of minecraft goes. I imagine in a few years we’ll have a way to train them on good and bad builds, give them a better concept of what constitutes a “building”, but what I’d REALLY love to see is some kind of simulation between them of an SMP, giving them access to baritone and allowing them to work out how to get things done in an open environment. Let their decision making guide them to the best path. Have them identify problems and come up with contextual solutions. E.G. I’ve been attacked by monsters outside my home at night, the best course of action would be to light up the surrounding area and build a wall to keep monsters out.
Have them break that down into simply steps that don’t have to be ai powered but can just be automatic, craft torches, go strip mining to get resources for the wall, etc.
I saw a paper about a similar project a while ago where they put down LLM agents in a simulated town and the “people” in the town had a small memory where they remembered previous experiences and had some agency on what they wanted to do, one of them planned a Valentine’s Day party and invited guests to it entirely on its own with no input. Very interesting stuff.
The paper you're referring to was done to advance research in multi-agent cooperative llm systems but a better examples of this would be the "Voyager" minecraft-llm paper. I've just completed a masters in this area, and i'll say we could do this today, it's just it would be costly to train and we have better ways to use our resources than advancing minecraft ai. When making a minecraft AI for research purposes Minecraft is used only as a proxy for the real world, with the idea that if we can make a solution that is super general and solves minecraft it will solve real world useful tasks. If we start coding minecraft-specific tasks for it to do, we're distracting ourselves from the proxy and just making something to play minecraft.
as I've been watching this series I've been thinking about how cool it would be to have a mod that adds a ton of alien-like AI generated structures, it really feels like aliens looked at human architecture and tried to re-create it.
I can just imagine stumbling upon those pillars at 4:35 and following them all the way just to find an empty, strange looking building with seemingly no purpose. gameplay wise I imagine players would be disappointed but personally I'm just here for the vibes, and the vibes these buildings give off are immaculate.
I avoided using this word in my original comment because it gets a bad rep, but the whole vibe is very "liminal", it just feels like you're not supposed to be there almost. Everything feels unfinished, and unnatural. The pyramids were pretty good but the smaller structures like the colosseums really give off the vibes I'm talking about.
I agree a vast desert with these ai generated structure is so ominous and like you said liminal I hope someone makes something like that someday
This might happen actually i hope a modder do it, i would also like to have a AI npcs in the world, imagine wandering finding a npc and try to talk to him to either help u or do something for u, and imagine if they have random personalities, like some of them are agressive, some are not, some are lonely and act weird, i feel it would be insane
@@iish4d_w360 theres actually a minecraft mod trying to do that now, you need credits for it tho
tbh it would make a great base
There’s something really amazing and unique the even “incomplete” buildings are. Very symmetrically interesting patterns! Keep on making more of these tests and videos!
You can do "/gamerule commandblock_output false" to make it so that it won't display every single block that they place in the chat
Oh cool, will use that. Thanks!
@@EmergentGarden small mistake it's "commandBlockOutput" not "commandblock_output"
@@EmergentGardenI could see pros and cons of this. The reduction of the chat spam seems nice, but in the event that it starts placing blocks somewhere it shouldn’t (like what happened in this video), it might help to see the coordinates aren’t right and easily find where it was. It’s really just up to you which you prefer.
@@Sniper1.1 interesting. Hadn't considered that
Uhhh maybe also sendcommandfeedback bc like that's for command blocks. I don't think they use command blocks (also ik there is probably something else there but I use bedrock)
I love videos like this that just explore what AI can currently do and treat it as a novelty to play with, rather than making any grandiose promises or predictions.
The societal implications of this tech are huge of course, but we can also just slow down, take it in, and play some video games.
What happens if you ask the AI to build esoteric concepts? Like "build the meaning of life" or something bizzare and conceptual like that.
It will probably make something shit.I is really hard for them to work even if proper prompt were given
Dirt blocj
it builds the library of babel
It was a good choice giving the bots cheats.
6:00 omg that actually caught me off-guard holy moly
I dont get it
@@HappyPlaysWasTaken the perfectly made rainbow sphere is really impressive
yeah same, maybe i am just easily impressed but when gpt built that i really thought "wow thats so cool!"
I would love these AI bots building liminal spaces in minecraft. It would totally feel disorienting.
That would be epic
100% agree, AI is very creative and I can imagine them doing that in the future for sure
A procedurally generated liminar dream/nightmarescape
OMG you are genius
[・・]
@@FFA-fg2bl "AI is very creative"
I wonder how it would handle a prompt asking it to make a maze or labyrinth
this guy hit a gold mine with these videos, endless ideas. Id like them to try to build cities or towns next.
11:08 lmao. When I was 9 in 2011 I got operator to a small server that had world edit. So I wanted to build a huge hollow glass sphere in the sky... but I set it wrong and the server crashed. When I re-logged, parts of the world for hundreds of blocks were made of glass shapes that weren't quite fully rendered into the giant sphere I had tried to create.
9:38 the music combined with "built it on top of failed pyramids" is so emotional.. makes me want to cry. Stellar video !!
The failed pyramids actually worked out in their favor too, like a supporting platform that made it look better I love it
Are the models integrated with vision, or is it literally just "blindly write code and hope for the best" ? I know it'll be expensive, but imagine if you supplied the model with periodic screenshots.
It has vision but not in way we have. It basically has coordinates of blocks nearby not like it can actually see anything it created. All of these things are just numbers to them
@@braineaterzombie3981 I'm just saying, most of these models (not sure about Llama, but it's open source so I'm sure people have made Llama Vision or whatever) have vision capabilities. As in, you can send them pics and they'll understand.
Not EXACTLY the same as how we humans 'understand' images, but good enough for use.
@@braineaterzombie3981they do have vision, like in "image data input". 4o even also has audio input (and output even). Passing stream of images still hasn't been released yet, but it's possible with 4o
For now we can pass occasional screenshots to gpt4o, gpt4vision and Gemini 1.5
@@braineaterzombie3981it knows where it is because it knows where it's not
I'm pretty certain in this case it's the latter
Survival test! It would be the best thing to just have a survival and have these slaves to mine and get wood. Would be so funny.
You should see if this can be used to help with the build the earth project. This might actually make it possible with further developments.
Genius idea
@@Nitekom Thank you
As someone who is tinkering with writing AI and loves Minecraft I thank you for making these videos.
You can also use /fill command to make it even faster if you are doing cuboid etc or use worldedit for more complex stuff like spheres.
Worldedit also has a handy undo function. I have to use it a lot.
this is awesome dude, im so invested in this project
I just started to watch the video and immediately he says “See those buildings, I’m gonna fly into them” lmao
Genuinely one of the best things I've seen done with AI, this has actually given me build ideas
This creations will only get better and more advanced as the LLM's get more advanced. Really looking forward to what these are capable of. Subbed!
This is a much bigger deal than the narrow domain of minecraft.
You’re showing how we can augment the capabilities of the models with better design choices for how they navigate their task.
This is a multiplier on algorithmic / scaling improvements for future models.
0:05 september time
I wonder if it would help to use a multimodal model and automatically take screenshots of the building for feedback so the model can iterate until it judges it to look good.
it has the data of the area around it
These kinda remind me of the feeling of the original backrooms with these structures that are almost human but are very clearly not human at the same time
"Don't worry I'm not gonna crash into them" - proceeds going straight into that shining tower
I believe for the /setblock command you can use keep and it'll only change the block if it's an empty air block - then, if something goes wrong while the bots are building, you could tell them to just replace everything they just built with air as a sort of "undo" feature
I like that some of these look a little alien, that one listing pyramid with all the gaps feels so strange. That Parthenon, colosseum, all have a strange, nearly otherworldly aesthetic, vaguely recognizable but still strange. I like it.
Your content is awesome. i love these lil guys doing stuff in minecraft but i want to see like tutorials at first 2 minutes of the next video about how to set up!
this project is so cool, it's so interesting to see the different LLM interactions in the game, i'll keep tuning in ! great work !
Loved the pyramid build. Thanks for sharing your progress/experience with Mindcraft
i LOVED the first build at the beginning. it's so beautiful! it's a real work of art.
this is by far my most anticipated AI projects. I canot wait to try it in the future when it's a bit more stable and easy to use
Cool video! I remember once having an idea, it would be cool if there was a server where only AI players would play, who would self-learn thanks to live players, after which it would be difficult to distinguish them from real people, they could communicate with each other, build houses and grief each other
I'm fascinated with all your work. A very different but understandable way to show the comparative potential of the various models. And one can only imagine how videogames are going to look like in 3 years time. We are truly at the doorstep of a new Era.
This guy is a legend, in less than 30 seconds in he already made a two tower joke that includes planes. (You know what i mean)
I can already anticipate how much of a headache this would be, but getting the AI to build with worldedit would just be awesome.
the tower joke was funny but seeing what the ai built blew me away. what a ridiculous improvement. I love these videos
The Parthenon* the AI built has a great vibe. An Abstract psuedo roman structure, and broken up columns floating in neat rows away from it in a flat plane. I can see something like this being used in a story about something otherworldly. Precursors, an AI ran cyberspace being broken, a depiction of heaven, etc.
Accidental AI art.
Imagine the possibilities. An interesting idea would be to see how he can change the world, ask him to delete everything and create something else to see his capabilities... it would be incredible
This is amazing. I must try it!
That giant pyramid looks like it might be as big as the one cubfan built in Hermitcraft SMP a couple seasons ago.
Being a PHD student while doing this is insane work. I'm sure you have a blast making these vids
You could use a greedy-meshing-like approach (but with volumes instead of faces) to post-process the AI's output into chunks of the same block type. Then you can use fill commands to place multiple blocks at once, which would make it much faster.
Btw I believe you can also disable chat messages for commands, so the chat is not spammed with setblock messages.
Damn, that's a huge improvement 🤩🤯I hope more people will see this channel 😊If in the future we can get the models to understand us more carefully and take longer to write the proper code, it'll be awesome. Right now, every AI from every field is trying to make stuff as fast as possible, so they make a lot of mistakes and we have to iterate multiple times 😅I wish they would just take their time and do it nice, i don't care if i have to wait 2 min instead of 10 sec.
A while ago I tried to get this working, but they were blissfully unaware of their code not working, or that they had previously written code. I might be able to get it working now, but I"m 100% demotivated. I'll just watch your videos instead. Also, you thought about experimenting with instructing the agents to build a fully functional vanilla neural network?
I find it cute that the AI can be proud if itself, like Claude saying that it's happy with how its builds turn out
These are pre programmed responses dude
Looking forward to the setup tutorial!
6:27 SANS
You: hmm interesting its made out of concrete, glass and glowstone
Also you: please build it out of concrete, glass and glowstone
6:13 that colored shadow is crazy
0:20 light looks so nice
I love this kind of vids so much, ty
If you want to fill a place with the same block just use /fill command instant of placing every block with /setblock .
If anyone sees this, I need an explanation.
I still don’t rly understand how the AI is kinda just building in Minecraft. It’s just a language model. Is it just coding and that code is put into “mindcraft” then it translates that code into the characters doing something?
And how does it kinda just automatically build something? I don’t get how AI is using cheats.
And how is the code that AI is creating to build different from mojang’s code that is used to create terrain and villages and stuff?
"Is it just coding and that code is put into “mindcraft” then it translates that code into the characters doing something?"
Basically, yes. They write code that gets executed in the game, "mindcraft" being a framework to facilitate that.
"And how does it kinda just automatically build something? I don’t get how AI is using cheats."
The agents build internal representations of the world, use those to plan buildings, and write code to implement the plans. That's an oversimplification, but yeah. The cheats are just code in the games codebase, and are called from the command line like other functions. They need to be enabled by setting allow cheats to true, IIRC.
"And how is the code that AI is creating to build different from mojang’s code that is used to create terrain and villages and stuff?"
The agents build only what they're told to, but they can create new designs. The game code has static designs for everything.
These are all just my observations.
"See those towers over there? Yeah i coded Gemini to fly into them using this new Plane Mod"
im watching this while rendering a 12:03 minute long video lol
Love the new approach and transcendental build sophistication - gotta love that!
Can't wait when you test Sonnet 3.5
I love these Ai building stuff in minecraft videos
Blind Spots is the best minecraft beta song
Seriously underrated video and channel. Here before your impending immense blow up
I think i understand why Llamas skyscraper was so short. It is ten blocks (floors) tall so theorethically it did the assigned task right, it just so happened that what the AI considered a floor and what you considered a floor differed. It just thought that floors don't also need some hollow space in between them.
This is so cool because it sort of offers us a way to almost visualize the way the neural networks formed the "understanding" of concepts.
So satisfying how quick and dirty a.i. this can be used to develop new worlds for Minecraft. Definately next gen gaming for minecraft.
Imagine in the future making new survival words each with unique structures made specifically for that world
I'd love to see them try something with commands/command blocks, like "hey gemini, drop me a pair of unbreaking 2 boots that also apply a haste affect". Could be useful for SMP servers
I am currently doing a similar thing with AI. I am writing a python script to nearly mimic the functionality of chatGPT, with my own added features such as file creation, txt file reading, and internet searching. I also created a makeshift memory for it, that allows it to recall past conversations even if you restart your computer or the model. All of this runs locally. The issue im running into is having it write commands to execute these different functions.
I've never seen A.I more expressive than in this
The sphere at 6:05 is honestly impressive.
Especially the shadow it casts.
I honestly never thought GPT could make something so intricate.
I just saw the last video, and wow! What an improvement! Is this possible with WorldEdit commands? Originally, that's what I assumed the 'cheats' were. Watching the build step-by-step with setblock is really cool to watch, though. The super large circles with almost zero error, and the large glass spheres especially were impressive. Pushing the forefront of minecraft technology.
We need an AI redstone building contest where they build a lot more complicated redstone builds
With the multimodal llms, you can probably get it to take an automatic picture of the build, ask the llm to critique it's build, then iterate!
I still see a huge gap with AI; it cannot SEE what it is building as it's making it. there isn't even a workaround (that I can think of) for this, which means that they will continuously be unable to notice and fix their own bugs in their code
If you watched one of the previous videos, Claude realized it made a mistake in the middle of building and tried to correct it, only it ended up building the second house into the first house
16 seconds in and you earned a Subscribe... Worth it, and valid.
Would be great if they could make some map arts!
i could watch these guys build random nonsensical architecture for a while. looking forward to the tutorial video, want to be able to do this myself
You could possibly write code manually to check if the block being placed is more then a certain distance away from the bot to prevent accidental griefs, maybe make horizontal and vertical different values though in cases like its tower
this is my new favorite genre of mc youtube
that first face got me good
This is really cool, we can't lie about that. Have you discovered anything new with the AI's since this video? When is your next one? I'm really enjoying your videos, your showcasing of their abilities are fun to watch.
This is one of my favorite AI projects to follow, particularly because of the rapid advancement of AI and the growing competition in the LLM market. Comparing the capabilities of different AI agents in Minecraft is such a novel and awesome idea, like something straight out of the Matrix. Just imagine how advanced these bots would be if they utilized Multimodal models such as GPT-4o!
I hope that one day when computers are powerful enough someone would create a mod that incorporates one off ai generated buildings into minecraft survival gameplay, it would make minecraft feel more mysterious and fun kinda like the feeling we get back when we just started playing minecraft without knowing much about gameplay mechanics
It'd be cool to see them try and build something in survival start to finish. With LLMs as the glue between the cracks of Mineflayer, I'd be curious to see if, given a schematic or something, the bots were able to find and craft resources to create them
It’d be quite to explore the maps of the worlds you use in these videos, if you decided to release them, that’d be really cool!
Something that would be interesting is seeing how the models fare in making redstone projects & logic. I doubt they would see much success seeing as they struggle with pyramids but it'd be fun to watch if nothing else
Can't wait to see how Claude 3.5 sonnet will do!
Gemini is like that one kid who plays sports but sucks at it but nobody tells him but they just act like his friend
Are u able to use gpt-4o aalready and is it better than gpt-4? Also gpt-4o might be even better with the vision aspect.