Gemini 1.5 is generally available via Vertex AI since a couple of days. You can also create an API key via AI Studio; it's not only their chatbot interface and a little easier to create an account.
I find the fact that the scaffolding is different when it so easily could repeat the same pattern of scaffolding for the same pattern of blocks being placed
I dont know why but its so cute seeing the AI use dirt as scaffolding even though they're in Creative. I really wonder what they would build if you gave them really abstract concepts.
Ideas you should try to make them do: raid deep dark city, raid bastian, kill a warden, defeat a raid. Also can they breed animals and cure zombie villagers back to villagers.
just for the laughs get the models to try and complete all the mine-craft quests/tasks. see which one completes first with the fewest re-spawns. don't tell them that is the aim. more so just try to evaluate how they go about completing the game. also if you put all the models in the same world and allow them to talk to each other see if they collaborate with each other at any point
I want to know how you set this up I've got some ideas like having them build pixel art or a tnt canon. or even something like a simple flying machine with 2 pistons, slimeblocks, and an observer.
it looks like he's using PrismarineJS/mineflayer and just asking chatgpt to write scripts for it. it's just simple stuff, no machine learning here, it won't be able to do anything special.
Correct me if I'm wrong but Minecraft has a scaffolding block that if you break the bottom block the supporting block in a column. All the higher blocks break as well. Why not just use the scaffolding block as scaffolding?
What if, in survival, you ask them to get as many achievements as possible? (Maybe with no further explanation of how to do it than what the game give, and see where they could go...)
do you have an educational content of how to use ai features in minecraft or generally in games. I would really like to learn some details of this even a little bit.
it makes me shake violently when i see a language model used for something like this. Yes ik its writing code to do this but id love to see more support for things like mineRL
To do this effectively, we’d need a system to take a structure file and decompose it into an algorithm, which would be a bit tricky but doable. And we’d need a ton of reference structures
I think we could do that with a 3 dimensional array, assigning Id and coordinates to each block, yet gathering a ton of reference structures would be insanely hard
10:28 that "does anyone know where i can find some" makes me really want to see these ais try to do something together. like just set them loose in survival mode and see what happens
Imagine they do a Prometheus and escape his PC, upload themselves to the internet, manage to build themselves a body then travel to Emergent Gardens house to wake him up
It is still interesting to see these LLMs do their best at understanding how to build in Minecraft, i wonder if more of them ever get image scanning abilities, you could let them take pictures of builds or the environment so they can see what they built and they can auto-correct?
Gemini vision is really good for images and is able to process minecraft screenshots. No way it will get coordinates of missing/wrong block correctly tho. Maybe it is possible to create some resoursepack/mod to write block coordinates on its faces?
@dapperwolf465 no, its the same issue thats always been the case, where porn is always leading the bleeding edge of technology, no matter what field of technology.
I don't have friends like I used to at childhood and I'm hoping AI can play Minecraft with me because I would love having another player even if it's AI build buildings, exploring and doing lot of fun Minecraft stuff, as a 19 years old no peers would like to play Minecraft because it's a childish game they say
I don’t know exactly how your system works but have you tried letting them use something like mathematical curves for building? Like vectors at positions pointing to positions with some formulas on top if required? Another thing you could do to help them out is allow them to write classes per object in a build. I think this would be great for things like columns because they then realise there would be spatial rules like spacing.
@Emergent Garden Recommendation from me: Your prompts have no leverage, what I mean is that the LLM does not handle complex building tasks well because its limited by the single shot answer it needs to generate. Your template for "NewAction" is a great idea, my idea to improve its leverage is to add another template "NewActionPlan" Which it then fills with a list of generated prompts that will then be fed back into itself one after another (kind of like writing a todo list before getting started) My vision for it was kind of like this: -You whisper"Build a bridge for me" - "Okay lets plan this out" *used newActionPlan* - Okay lets see whats first on the todo list... *used actionPlan[0]* Sure I will build the supporting pillars *used newAction* ...etc Getting a shared reference point for superimposed building actions is of course something to consider. Using plans recursively might also be interesting, like making a plan for planning multiple plans for even more abstracted tasks. Some way of sensing the world is possible, maybe you can let it take screenshots of the game and feed the image into some of the multi modal image recognition capable models
I haven't tested it extensively with GPT-4o yet, but in my experience with Gemini and GPT-4 on other tasks, vision has feedback doesn't work super well. I often tried creating diagrams with python, SVG images, images generated by DALL-E, graphical user interfaces and more. While the models were able to produce pretty decent outputs for most of these tasks, they all required many prompts and detailed instructions put in manually. Inputting images of their current results almost never lead to significant improvements. I'm sure that eventually LLMs or similar models will be able to do that, but from my experience, we're not there yet (with published models at least).
i think it would be cool if you let every iteration build a skyscraper and add them all to a single city which will then grow with skyscrapers that are slowly getting better so you can see the improvement in one place
4:08 In Llama's defence, I can see how those could be described as one-block columns spaced 'one block apart' as requested at 2:48, it's just included the column itself in the measurement of 'spaced'.
Doing this without computer vision is interesting and really makes me appreciate how incredibly complex the human brain is to be able to do so much in real time. Imagine the resources needed to give a multimodal model with vision/language/action the ability to _play_ in real time, the power requirements, where we can just eat for energy
Woldn't be interesting to have naturally generated structures in the world built by AI, instead of finding the same structures over and over you could find useless, not so good looking and simple but surely enigmatic structure to give minecraft his old feeling of mistery and the feeling of seeing for the first time like in the old days
Remember when Chess Engines came into existence? Now people held tournaments for Chess Engine AIs to beat each other. Soon, Hunger Games and Bed Wars matches will be played by AIs as well, for our entertainment. With the creative world of Minecraft, god knows what else AI can do in a server... They can achieve greatness, even better than all what we have ever did as a species...
I don't know what you're doing to get such success, but I couldn't get any model to do anything right. Almost as if it's the anti-pattern, 100% failure. No matter how simple the task, none seemed to be able to do anything.
Hey EG! I have a question (I know very little about AI) As a minecraft player we sometimes use "structure blocks" to select and save a region of blocks. The saved NBT file can be exported to anyone who wants your creation in their own world. There are literal thousands of NBT files online... would it be possible to train an AI to generate NBT files?
It's possible, but very expensive. That data is quite complex, requiring huge amounts of compute resources to train any useful AI. Most current AI techniques also require labels for the data. So the data for a house isn't enough, you also need a detailed text description. There are similar things that have been done though. I think NVIDIA has an AI that can generate 3D models based on text prompts, not in Minecraft, but some are fae mire detailed than a small minecraft build could be. It's a very similar concept.
That already exists, also there is a bot that mines for you diamonds, or any other material you need xd But of course, unlike AI, those can't create code by themselves.
I suppose I should be glad people take seriously the part where I imply there not existing such bots already, instead of taking seriously the part where I tell them I'm looking forward to automated griefing 😂
Yeah, mineflayer-pathfinder definitely needs some improvements, especially in the scaffolding department. Maybe I can get myself to work on it some more. This is actually not the first time people tried to use general ai with mineflayer. There was also a French Microsoft team that did the same before with gpt. I think having the agents write the code has huge potential, especially if the modells were trained on the existing mineflayer code.
You could probably create a really powerful diffusion model for generating minecraft buildings if you managed to obtain a dataset for it. The blocks would be the equivalent of pixels, and the noise would be in the form of random blocks. A dataset could probably be gathered from those servers where players build on plots of land, or perhaps a mod could be made to allow users to independently mark and tag creations in their own worlds/servers.
@@deltamico Yeah idk how you would solve that part. Maybe the average rgb values of the block would work for standard blocks, and then an additional value could categorize its shape (i.e. panes, stair types, fences, candles...) I really have no idea what I'm talking about
Map all minecraft blocks to vectors in an n-dimensonal feature space using machine learning to find suitable eigenvectors (kinda like how LLMs turn words into vectors) then treat each pixel as a vector and proceed as normal. If your machine learning picks the right eigenvectors and enough of them it might work.
I think, the main issue here is the design of the workflow. LLMs are, afterall, LLMs, they're not building stuff incrementally, step by step, they are programming actions without seeing the result of their previous step. This can be solved with better prompts, ofc, but I still think it's not enough. We probably need some combination of computer vision with llm with custom training data, or even another architecture of neural network.
Can't wait for multimodal inputs with this project :) Having the ability to see what they're doing might even mean they don't have to write code to make the actions but rather can respond to the outcomes of their actions
Dead Minecraft theory. Servers flooded with bots controlled by AI that respond in near human like fashion, build their own cities, occasionally engage in pvp with each other. I want to see it. And we surely will in the coming months/years. I would love to join or host a server with hundreds of AI players living their artificial lives.
I love the way that your videos are presented, but this one in particular was really cool. Right now, the AI are silly and fun and a little bit mysterious; we bestow on them a personality given the first opportunity, too. Exploring and experimenting with this newer technology on a game that couldn't have conceived of it when it was released is fascinating. Imagine playing Minecraft with an AI companion that is not only adapted to beat Minecraft, but to play it. To explore, to build, to fight mobs and chat; it doesn't have to be a real player at all, but it's really good at acting like one. It could soon reach a point where, just watching them play, you really can't tell. I can see GPU only models trained entirely on Minecraft builds, or even highly playing parameters. Personally, I would love to see an AI capable of building really great stuff.
Imagine having a team of AI agents to keep you company in the long lonely hours of Minecraft. To not only help you with manual labor but also to keep you company when your friends are disinterested in playing with building blocks.
About the scaffoling thing... try telling them to use the actual scaffold block for that, which can be easily removed later just from below of the construction
dystopian adjective dys·to·pi·an (ˌ)dis-ˈtō-pē-ən variants or less commonly dystopic (ˌ)dis-ˈtō-pik -ˈtä- Synonyms of dystopian : of, relating to, or being an imagined world or society in which people lead dehumanized, fearful lives
the models have been trained on solving probability problems with characters and words. Had they been trained on (wasd) clicking and else, whow far would the be now. having to transcend a second dimensional barrier as a language model is quite challenging and im very impressed.
Gpt went like: U SAID COLUMNS, YOU GOT THEM.
When are we getting their group speedrun attempt to beat the dragon?
it probably will be a while, like once these bots get full vision capabiltiies
@@aienthusiast618 gpt-4o might have a chance
a manhunt between them 4
Train they must
yassssssss
“Ok go make a castle”
Llama: “birthday cake got it”
Gemini 1.5 is generally available via Vertex AI since a couple of days. You can also create an API key via AI Studio; it's not only their chatbot interface and a little easier to create an account.
1:28 llama(animal): who the heck are you?
Llama (AI): im you but better.
I find the fact that the scaffolding is different when it so easily could repeat the same pattern of scaffolding for the same pattern of blocks being placed
this is what AI is meant to be used for
I got shivers when gpt 4 entered the Nether and was confused
Your work is really fascinating, I haven't seen anything like this
There's something so interesting and fascinating in both teaching AI and AI themselves figuring out how to play minecraft.
The Nether. I got a nice chuckle out of the bit. Incredible.
9:31 LLama be like : Well i just copy his homework it's gonna be fine.
Not me audibly shouting "HOLY SHIT" when gpt4 actually completed the portal
Have you thought about trying to get them to build existing structures? Like a desert temple or something? Could be interesting
To remove scaffolding, I suggest it target the highest dirt block and remove them all from the top.
Watching AI's attempt to build stuff in Minecraft feels very surreal. The fact we even got to this point is strange. I love watching this though!
this may well be the very first time an ai has built a portal to the nether and entered it
Gpt4 was just like: Aight Imma head out
I lost my shit when GPT 4 stared you down as it became the first LLM to reach the nether.
I dont know why but its so cute seeing the AI use dirt as scaffolding even though they're in Creative.
I really wonder what they would build if you gave them really abstract concepts.
the Roman style building by gpt 4 is literally the room from 7-2 ultrakill
10:17 Imagine when it will actually be possible to just show the AI like he does here. They will eventually be able to learn that way.
GPT4 nether reaction: Whataheeeeeeeeeeeeeeel no wayayayayay
There’s so much potential for AI in gaming. Imagine the MineColonies mod but each NPC is actually intelligent and responds to what you do and build.
Llama is just happy to be there
low key here for llama's brutalist structures
A cool update: a bot that uses the /place command to speed up the process
Ideas you should try to make them do: raid deep dark city, raid bastian, kill a warden, defeat a raid.
Also can they breed animals and cure zombie villagers back to villagers.
@Google, you do NOT want to be on cactus collecting duty. Trust me.
can you make a tutorial video on how to use mindcraft?
I would really like to see a build battle against these bots
GPT wanted to finish his castle's build, but was stopped by you.
Gpt helping was just cute man!
i haven't started the video but i already know it's gonna be great.
just for the laughs get the models to try and complete all the mine-craft quests/tasks. see which one completes first with the fewest re-spawns. don't tell them that is the aim. more so just try to evaluate how they go about completing the game. also if you put all the models in the same world and allow them to talk to each other see if they collaborate with each other at any point
Am I so early that the bitrate is low due to the video still being processed, or is it just low?
The bitrate is still being processed.
I want to know how you set this up I've got some ideas like having them build pixel art or a tnt canon. or even something like a simple flying machine with 2 pistons, slimeblocks, and an observer.
it looks like he's using PrismarineJS/mineflayer and just asking chatgpt to write scripts for it. it's just simple stuff, no machine learning here, it won't be able to do anything special.
Wowie! Soon ai can replace having friends :)
llama is thinking outside the box.. which means there is no inside the box
note: this is MINDCRAFT
So this is how Mojang makes their naturally generated structures lol
got scary when gpt4 entered the nether
Correct me if I'm wrong but Minecraft has a scaffolding block that if you break the bottom block the supporting block in a column. All the higher blocks break as well. Why not just use the scaffolding block as scaffolding?
What if, in survival, you ask them to get as many achievements as possible? (Maybe with no further explanation of how to do it than what the game give, and see where they could go...)
do you have an educational content of how to use ai features in minecraft or generally in games. I would really like to learn some details of this even a little bit.
gpt4 went to hell, took a look and was outta there 😂
could u basically ask it to create an optimized minecraft play trough and ask them to try and exicute it? or is that wayyy to much for them?
What about making them able to use flight? No need for scaffolding if you can fly
I thought i was all ready subscribed 😂
it makes me shake violently when i see a language model used for something like this. Yes ik its writing code to do this but id love to see more support for things like mineRL
Could you have it use leaves as scaffolding? They would decay and remove themselves after a while
Player placed leaves don’t decay
Woooow INSANE 🤩🤩🤩🤩🤩
🤯🤯🤯🤯🤯🤯🤯🤯🤯🤯🤖🙏
You could simulate a civilization with those lol
@google give this man gemini 1.5 access I COMMAND YOU
what would happen if you let them communicate to each other in plain text and told them to try to cooperate could they organise?
I think we should train AI off the builds already built by players, like picture generation AI is trained
To do this effectively, we’d need a system to take a structure file and decompose it into an algorithm, which would be a bit tricky but doable. And we’d need a ton of reference structures
I think we could do that with a 3 dimensional array, assigning Id and coordinates to each block, yet gathering a ton of reference structures would be insanely hard
This is so funny to watch😂😂
Here are some people i suggest you collab with
Terahd
Matbatwing
Could you up your FOV a bit? It feels a bit cramped, but maybe that's just me being used to "Quake Pro"...
Very interesting though! I love it
GPT4 going to the nether was hilarious
WIDE PORTAL
mission failed successfully
“Gg! Come here!”
“NOPE” goes back in portal
not really
@@It-b-Blair couldn't found the players' location so it whent back to overworld i geuss
9:33 the way LLama kept trying to flip the switch as if it’ll make the lamp light up somehow 😂
maybe the switch was broken
it worked on his machine
ikr it was cute
10:28 that "does anyone know where i can find some" makes me really want to see these ais try to do something together. like just set them loose in survival mode and see what happens
Imagine they do a Prometheus and escape his PC, upload themselves to the internet, manage to build themselves a body then travel to Emergent Gardens house to wake him up
Peaceful mode might actually work.
@@Faitalalmfao
Imagine they build a pc in minecraft using redstone to produce more ai models using minecraft.@@Faitala
i saw it too
the aliens gave egyptians creative mode? I see!
Just like they gave Greeks democracy
It is still interesting to see these LLMs do their best at understanding how to build in Minecraft, i wonder if more of them ever get image scanning abilities, you could let them take pictures of builds or the environment so they can see what they built and they can auto-correct?
i think gpt 4 has image capabilities.
Gemini vision is really good for images and is able to process minecraft screenshots. No way it will get coordinates of missing/wrong block correctly tho. Maybe it is possible to create some resoursepack/mod to write block coordinates on its faces?
@@ИванКонобейцев-ш4б so is gpt, gpt can recognise what game your playing and get pretty accurate with spatial awareness
GPT 4o is getting live screen sharing capabilities with their real-time voice conversation, so it's going to be interesting.
@@ИванКонобейцев-ш4бgood idea potential applications in the build the whole world in Minecraft project
It's actually cute watching these AI models try
the future of gaming looks amazing, imagine having multiple ai bots that help you in your world all dwarf fortress style base building
already exists, try put the girlfriend/waifu mods
@@mastermentheis there one that isn’t so weird? Aka not virtual girlfriends or wafus tbh that’s kinda sad it exists
@dapperwolf465 no, its the same issue thats always been the case, where porn is always leading the bleeding edge of technology, no matter what field of technology.
I don't have friends like I used to at childhood and I'm hoping AI can play Minecraft with me because I would love having another player even if it's AI build buildings, exploring and doing lot of fun Minecraft stuff, as a 19 years old no peers would like to play Minecraft because it's a childish game they say
@@mastermenthe It's the strongest program in animals, which we belong to
I don’t know exactly how your system works but have you tried letting them use something like mathematical curves for building? Like vectors at positions pointing to positions with some formulas on top if required?
Another thing you could do to help them out is allow them to write classes per object in a build. I think this would be great for things like columns because they then realise there would be spatial rules like spacing.
@Emergent Garden Recommendation from me: Your prompts have no leverage, what I mean is that the LLM does not handle complex building tasks well because its limited by the single shot answer it needs to generate.
Your template for "NewAction" is a great idea, my idea to improve its leverage is to add another template "NewActionPlan" Which it then fills with a list of generated prompts that will then be fed back into itself one after another (kind of like writing a todo list before getting started)
My vision for it was kind of like this:
-You whisper"Build a bridge for me"
- "Okay lets plan this out" *used newActionPlan*
- Okay lets see whats first on the todo list... *used actionPlan[0]*
Sure I will build the supporting pillars *used newAction*
...etc
Getting a shared reference point for superimposed building actions is of course something to consider.
Using plans recursively might also be interesting, like making a plan for planning multiple plans for even more abstracted tasks.
Some way of sensing the world is possible, maybe you can let it take screenshots of the game and feed the image into some of the multi modal image recognition capable models
13:40 is that a pp?
It took me a second to see it
is it possible to use GPT-4o vision capabilities to let it "see" what is doing? That could significantly improve the quality.
I haven't tested it extensively with GPT-4o yet, but in my experience with Gemini and GPT-4 on other tasks, vision has feedback doesn't work super well.
I often tried creating diagrams with python, SVG images, images generated by DALL-E, graphical user interfaces and more.
While the models were able to produce pretty decent outputs for most of these tasks, they all required many prompts and detailed instructions put in manually.
Inputting images of their current results almost never lead to significant improvements.
I'm sure that eventually LLMs or similar models will be able to do that, but from my experience, we're not there yet (with published models at least).
i think for this to work it would need to be one integrated system as opposed to the mind flayer mod and api separately
Coming soon
you know we are doomed when gpt doesn`t know how to do an or gate but loves tnt
LLAMA: dahhh lets build a solid block house☝️🥴
mm cube
wait till llama figures out how to set people on fire
i think it would be cool if you let every iteration build a skyscraper and add them all to a single city which will then grow with skyscrapers that are slowly getting better so you can see the improvement in one place
This is idea is goated, I low key wanna see this, this project has so much potential
4:08 In Llama's defence, I can see how those could be described as one-block columns spaced 'one block apart' as requested at 2:48, it's just included the column itself in the measurement of 'spaced'.
11:12 its so cute how Gpt ran away 😭
Doing this without computer vision is interesting and really makes me appreciate how incredibly complex the human brain is to be able to do so much in real time.
Imagine the resources needed to give a multimodal model with vision/language/action the ability to _play_ in real time, the power requirements, where we can just eat for energy
this is SO cool! gpt4 going to the nether had me in awe
Woldn't be interesting to have naturally generated structures in the world built by AI, instead of finding the same structures over and over you could find useless, not so good looking and simple but surely enigmatic structure to give minecraft his old feeling of mistery and the feeling of seeing for the first time like in the old days
You would probably have more luck designing a specialized generative model for 3d buildings, I think.
You can prolly use diffusion methods for that lowkey.
@@Luuuuuuuuuuuuuuuuuuuuuuuuuuu Elements Engine!
@@honkhonk8009 minecraft diffusion models would go crazy
Love this project!
Remember when Chess Engines came into existence? Now people held tournaments for Chess Engine AIs to beat each other. Soon, Hunger Games and Bed Wars matches will be played by AIs as well, for our entertainment. With the creative world of Minecraft, god knows what else AI can do in a server... They can achieve greatness, even better than all what we have ever did as a species...
I don't know what you're doing to get such success, but I couldn't get any model to do anything right. Almost as if it's the anti-pattern, 100% failure. No matter how simple the task, none seemed to be able to do anything.
Hey EG! I have a question (I know very little about AI)
As a minecraft player we sometimes use "structure blocks" to select and save a region of blocks. The saved NBT file can be exported to anyone who wants your creation in their own world.
There are literal thousands of NBT files online... would it be possible to train an AI to generate NBT files?
It's possible, but very expensive.
That data is quite complex, requiring huge amounts of compute resources to train any useful AI.
Most current AI techniques also require labels for the data. So the data for a house isn't enough, you also need a detailed text description.
There are similar things that have been done though. I think NVIDIA has an AI that can generate 3D models based on text prompts, not in Minecraft, but some are fae mire detailed than a small minecraft build could be. It's a very similar concept.
Already looking forward to automated 24/7 super effective and unkillable AI griefers on my servers. Ah, good times 😁
Those have already existed for 4 years
That already exists, also there is a bot that mines for you diamonds, or any other material you need xd But of course, unlike AI, those can't create code by themselves.
Those have existed for ages - you don't need neural network levels of intelligence to place TNT and break blocks.
I suppose I should be glad people take seriously the part where I imply there not existing such bots already, instead of taking seriously the part where I tell them I'm looking forward to automated griefing 😂
@@etunimenisukunimeni1302looking forward implies they will exist in the future
Yeah, mineflayer-pathfinder definitely needs some improvements, especially in the scaffolding department. Maybe I can get myself to work on it some more. This is actually not the first time people tried to use general ai with mineflayer. There was also a French Microsoft team that did the same before with gpt. I think having the agents write the code has huge potential, especially if the modells were trained on the existing mineflayer code.
The fact that they are imperfect makes it more amazing.
One day we might use AI to assist in building, or even do it completely independently, very exciting
You could probably create a really powerful diffusion model for generating minecraft buildings if you managed to obtain a dataset for it. The blocks would be the equivalent of pixels, and the noise would be in the form of random blocks. A dataset could probably be gathered from those servers where players build on plots of land, or perhaps a mod could be made to allow users to independently mark and tag creations in their own worlds/servers.
You'll need some methods for descrete diffusion since a variation in block's number results in a whole new block, similar to diffusion for text
@@deltamico Yeah idk how you would solve that part. Maybe the average rgb values of the block would work for standard blocks, and then an additional value could categorize its shape (i.e. panes, stair types, fences, candles...)
I really have no idea what I'm talking about
Map all minecraft blocks to vectors in an n-dimensonal feature space using machine learning to find suitable eigenvectors (kinda like how LLMs turn words into vectors) then treat each pixel as a vector and proceed as normal. If your machine learning picks the right eigenvectors and enough of them it might work.
I think, the main issue here is the design of the workflow. LLMs are, afterall, LLMs, they're not building stuff incrementally, step by step, they are programming actions without seeing the result of their previous step. This can be solved with better prompts, ofc, but I still think it's not enough. We probably need some combination of computer vision with llm with custom training data, or even another architecture of neural network.
Can't wait for multimodal inputs with this project :)
Having the ability to see what they're doing might even mean they don't have to write code to make the actions but rather can respond to the outcomes of their actions
Dead Minecraft theory. Servers flooded with bots controlled by AI that respond in near human like fashion, build their own cities, occasionally engage in pvp with each other. I want to see it. And we surely will in the coming months/years. I would love to join or host a server with hundreds of AI players living their artificial lives.
I would love to have a research Institute with the language and understanding capabilities become a sentient creature in a Minecraft world
ive never been too fond of ai but seeing these things run around trying to make lights work and blowing shit up is the best thing ever
I love the way that your videos are presented, but this one in particular was really cool. Right now, the AI are silly and fun and a little bit mysterious; we bestow on them a personality given the first opportunity, too. Exploring and experimenting with this newer technology on a game that couldn't have conceived of it when it was released is fascinating. Imagine playing Minecraft with an AI companion that is not only adapted to beat Minecraft, but to play it. To explore, to build, to fight mobs and chat; it doesn't have to be a real player at all, but it's really good at acting like one. It could soon reach a point where, just watching them play, you really can't tell. I can see GPU only models trained entirely on Minecraft builds, or even highly playing parameters. Personally, I would love to see an AI capable of building really great stuff.
The modern Turing Test, lol
Imagine having a team of AI agents to keep you company in the long lonely hours of Minecraft. To not only help you with manual labor but also to keep you company when your friends are disinterested in playing with building blocks.
Ngl this Is kind of a historical video
About the scaffoling thing... try telling them to use the actual scaffold block for that, which can be easily removed later just from below of the construction
You could build an SMP server with AI payers one day that feel like playing with friends
dystopian
adjective
dys·to·pi·an (ˌ)dis-ˈtō-pē-ən
variants or less commonly dystopic
(ˌ)dis-ˈtō-pik
-ˈtä-
Synonyms of dystopian
: of, relating to, or being an imagined world or society in which people lead dehumanized, fearful lives
your videos are so relaxing
the models have been trained on solving probability problems with characters and words. Had they been trained on (wasd) clicking and else, whow far would the be now. having to transcend a second dimensional barrier as a language model is quite challenging and im very impressed.
Trying AI feels like you're teaching a 4 year old how to play minecraft for their first time. It's cute and a bit scary.